{"source":"AIMap","schema":"benchmark/v1","updated":"2026-10-22","benchmark":{"id":"open-llm-leaderboard","name":"Open LLM Leaderboard v2","category":"general","unit":"%","higherIsBetter":true,"status":"archived","sources":["openllm"],"primaryVariant":"average","url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","year":2024,"desc":{"en":"Hugging Face's leaderboard of open-weight models, scored on IFEval, BBH, MATH Lvl 5, GPQA, MuSR and MMLU-Pro with normalised scores. The leaderboard was archived in 2025 and no longer accepts submissions.","zh-hans":"Hugging Face 的开放权重模型排行榜，用 IFEval、BBH、MATH 第 5 级、GPQA、MuSR、MMLU-Pro 六项归一化打分。该榜已于 2025 年归档，不再接受新提交。"},"measures":{"en":"Average of six normalised academic benchmarks, run by Hugging Face with the same harness.","zh-hans":"由 Hugging Face 用同一套评测框架跑出的六项学术基准归一化平均分。"},"limits":{"en":"Archived: no models after early 2025. Only open-weight models. We keep only models published by their original developers (no merges or community fine-tunes).","zh-hans":"已归档：不含 2025 年初以后的模型；只有开放权重模型。本站只保留原厂发布的模型，不收社区合并/微调版本。"},"contamination":"high","contaminationNote":{"en":"Fixed public test sets; the leaderboard itself flagged contaminated submissions.","zh-hans":"固定公开测试集，榜单本身曾标记过污染提交。"},"stats":{"results":311,"models":294,"latest":"2025-03-13","bySourceType":{"official":311}}},"sources":[{"id":"openllm","name":"Hugging Face Open LLM Leaderboard v2 (archived)","license":"No licence tag – factual scores only, with citation","policy":"facts","attribution":"Hugging Face, Open LLM Leaderboard (archived 2025)","site":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard"}],"results":[{"model":"qwen2-5-72b","modelName":"Qwen2.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":47.98,"unit":"%","rank":6,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-32b","modelName":"Qwen2.5-32B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-32B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 32.764B params","score":46.6,"unit":"%","rank":22,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-large-2-nov-2024","modelName":"Mistral Large 2 (Nov 2024)","provider":"Mistral AI","rawName":"mistralai/Mistral-Large-Instruct-2411","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 122.61B params","score":46.52,"unit":"%","rank":23,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-3-70b","modelName":"Llama 3.3 70B","provider":"Meta","rawName":"meta-llama/Llama-3.3-70B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":44.85,"unit":"%","rank":40,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-72b","modelName":"Qwen2-72B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":43.59,"unit":"%","rank":58,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-70b","modelName":"Llama 3.1-70B","provider":"Meta","rawName":"meta-llama/Llama-3.1-70B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":43.41,"unit":"%","rank":62,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-70b","modelName":"llama-3.1-tulu-3-70b","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-70B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":42.33,"unit":"%","rank":103,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"tulu-3-t-lu-3-70b","modelName":"Tulu 3 (Tülu 3) 70B","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-70B-DPO","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70B params","score":42.22,"unit":"%","rank":107,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-14b-instruct-1m","modelName":"Qwen2.5-14B-Instruct-1M","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-14B-Instruct-1M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.77B params","score":41.56,"unit":"%","rank":148,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-70b","modelName":"llama-3.1-tulu-3-70b","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-70B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 70.554B params","score":41.45,"unit":"%","rank":160,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-14b","modelName":"Qwen2.5-14B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-14B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.77B params","score":41.31,"unit":"%","rank":173,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aceinstruct-72b","modelName":"AceInstruct-72B","provider":"NVIDIA","rawName":"nvidia/AceInstruct-72B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":40.41,"unit":"%","rank":238,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"solar-pro-preview-instruct","modelName":"solar-pro-preview-instruct","provider":"upstage","rawName":"upstage/solar-pro-preview-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 22.14B params","score":39.94,"unit":"%","rank":272,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-32b-instruct","modelName":"Qwen2.5-Coder-32B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-32B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 32.764B params","score":39.89,"unit":"%","rank":276,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-vl-72b-instruct","modelName":"Qwen2-VL-72B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-VL-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 73.406B params","score":39.54,"unit":"%","rank":306,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-5-20b-chat","modelName":"internlm2_5-20b-chat","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2_5-20b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 19.86B params","score":38.88,"unit":"%","rank":348,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-70b-sft","modelName":"Llama-3.1-Tulu-3-70B-SFT","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-70B-SFT","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":38.85,"unit":"%","rank":351,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-3-llama-3-1-70b","modelName":"Hermes-3-Llama-3.1-70B","provider":"NousResearch","rawName":"NousResearch/Hermes-3-Llama-3.1-70B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":38.51,"unit":"%","rank":373,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-14b","modelName":"DeepSeek-R1-Distill-Qwen-14B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.77B params","score":38.22,"unit":"%","rank":392,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-math-72b-instruct","modelName":"Qwen2-Math-72B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-Math-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":38.02,"unit":"%","rank":408,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"exaone-3-5-32b-instruct","modelName":"EXAONE-3.5-32B-Instruct","provider":"LGAI-EXAONE","rawName":"LGAI-EXAONE/EXAONE-3.5-32B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 32.003B params","score":37.6,"unit":"%","rank":435,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-nemotron-70b-instruct-hf","modelName":"Llama-3.1-Nemotron-70B-Instruct-HF","provider":"NVIDIA","rawName":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":36.91,"unit":"%","rank":478,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-5-moe","modelName":"Phi-3.5-MoE-instruct","provider":"Microsoft","rawName":"microsoft/Phi-3.5-MoE-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 42B params","score":36.88,"unit":"%","rank":482,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-math-72b-instruct","modelName":"Qwen2.5-Math-72B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Math-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":36.82,"unit":"%","rank":488,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"acemath-72b-instruct","modelName":"AceMath-72B-Instruct","provider":"NVIDIA","rawName":"nvidia/AceMath-72B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 72.706B params","score":36.66,"unit":"%","rank":504,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-7b-instruct","modelName":"Falcon3-7B-Instruct","provider":"TII UAE","rawName":"tiiuae/Falcon3-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.456B params","score":36.4,"unit":"%","rank":530,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-70b","modelName":"Llama 3-70B","provider":"Meta","rawName":"meta-llama/Meta-Llama-3-70B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":36.37,"unit":"%","rank":534,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-27b","modelName":"Gemma 2 27B","provider":"Google","rawName":"google/gemma-2-27b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 27.227B params","score":36.17,"unit":"%","rank":555,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-10b-instruct","modelName":"Falcon3-10B-Instruct","provider":"TII UAE","rawName":"tiiuae/Falcon3-10B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 10.306B params","score":35.48,"unit":"%","rank":602,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-7b","modelName":"Qwen2.5-7B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":35.2,"unit":"%","rank":623,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwq-32b-preview","modelName":"QwQ-32B-Preview","provider":"Alibaba (Qwen)","rawName":"Qwen/QwQ-32B-Preview","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 32.764B params","score":34.12,"unit":"%","rank":717,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mixtral-8x22b","modelName":"Mixtral 8x22B","provider":"Mistral AI","rawName":"mistralai/Mixtral-8x22B-Instruct-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 140.621B params","score":33.89,"unit":"%","rank":731,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"command-r","modelName":"Command R+","provider":"Cohere","rawName":"CohereForAI/c4ai-command-r-plus-08-2024","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 103.811B params","score":33.65,"unit":"%","rank":748,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-1-5-34b","modelName":"Yi-1.5-34B","provider":"01.AI","rawName":"01-ai/Yi-1.5-34B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 34.389B params","score":33.36,"unit":"%","rank":767,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-32b","modelName":"Qwen2.5-Coder-32B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-32B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 32.764B params","score":33.26,"unit":"%","rank":770,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-110b","modelName":"Qwen1.5-110B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-110B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 111.21B params","score":33.13,"unit":"%","rank":776,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-medium-4k-instruct","modelName":"phi-3-medium-4k-instruct","provider":"Microsoft","rawName":"microsoft/Phi-3-medium-4k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13.96B params","score":33.1,"unit":"%","rank":778,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aceinstruct-7b","modelName":"AceInstruct-7B","provider":"NVIDIA","rawName":"nvidia/AceInstruct-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":33.06,"unit":"%","rank":786,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-57b-a14b","modelName":"Qwen2-57B-A14B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-57B-A14B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 57.409B params","score":33.02,"unit":"%","rank":788,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-5-7b-chat","modelName":"internlm2_5-7b-chat","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2_5-7b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7.738B params","score":32.97,"unit":"%","rank":792,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-7b-instruct-1m","modelName":"Qwen2.5-7B-Instruct-1M","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-7B-Instruct-1M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":32.76,"unit":"%","rank":798,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"exaone-3-5-7-8b-instruct","modelName":"EXAONE-3.5-7.8B-Instruct","provider":"LGAI-EXAONE","rawName":"LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7.818B params","score":32.55,"unit":"%","rank":809,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-small-7-4b","modelName":"phi-3-small 7.4B","provider":"Microsoft","rawName":"microsoft/Phi-3-small-8k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.392B params","score":32.34,"unit":"%","rank":828,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-14b-instruct","modelName":"Qwen2.5-Coder-14B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-14B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.77B params","score":32.12,"unit":"%","rank":838,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-9b","modelName":"Gemma 2 9B","provider":"Google","rawName":"google/gemma-2-9b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9B params","score":32.07,"unit":"%","rank":843,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-medium-14b","modelName":"phi-3-medium 14B","provider":"Microsoft","rawName":"microsoft/Phi-3-medium-128k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13.96B params","score":32.03,"unit":"%","rank":847,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deephermes-3-mistral-24b-preview","modelName":"DeepHermes-3-Mistral-24B-Preview","provider":"NousResearch","rawName":"NousResearch/DeepHermes-3-Mistral-24B-Preview","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 23.572B params","score":31.99,"unit":"%","rank":853,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-small-128k-instruct","modelName":"Phi-3-small-128k-instruct","provider":"Microsoft","rawName":"microsoft/Phi-3-small-128k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.392B params","score":31.97,"unit":"%","rank":854,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"c4ai-command-r7b-12-2024","modelName":"c4ai-command-r7b-12-2024","provider":"Cohere","rawName":"CohereForAI/c4ai-command-r7b-12-2024","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.028B params","score":31.62,"unit":"%","rank":880,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"c4ai-command-r-plus","modelName":"c4ai-command-r-plus","provider":"Cohere","rawName":"CohereForAI/c4ai-command-r-plus","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 103.811B params","score":30.94,"unit":"%","rank":921,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-2-8b-instruct","modelName":"Granite-3.2-8B-Instruct","provider":"IBM","rawName":"ibm-granite/granite-3.2-8b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.171B params","score":30.77,"unit":"%","rank":932,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-8b-instruct","modelName":"Granite-3.1-8B-Instruct","provider":"IBM","rawName":"ibm-granite/granite-3.1-8b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.171B params","score":30.6,"unit":"%","rank":945,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-4","modelName":"Phi-4","provider":"Microsoft Research","rawName":"microsoft/phi-4","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.66B params","score":30.36,"unit":"%","rank":969,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"acemath-7b-instruct","modelName":"AceMath-7B-Instruct","provider":"NVIDIA","rawName":"nvidia/AceMath-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":30.33,"unit":"%","rank":972,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-small-instruct-2409","modelName":"Mistral-Small-Instruct-2409","provider":"Mistral AI","rawName":"mistralai/Mistral-Small-Instruct-2409","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 22.247B params","score":29.92,"unit":"%","rank":1044,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aya-expanse-32b","modelName":"Aya-Expanse-32B","provider":"Cohere","rawName":"CohereForAI/aya-expanse-32b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 32.296B params","score":29.72,"unit":"%","rank":1075,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-1-5-9b-chat","modelName":"Yi-1.5-9B-Chat","provider":"01.AI","rawName":"01-ai/Yi-1.5-9B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.829B params","score":29.53,"unit":"%","rank":1105,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-4","modelName":"Phi-4","provider":"Microsoft Research","rawName":"microsoft/phi-4","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 14.66B params","score":29.48,"unit":"%","rank":1112,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-4-mini","modelName":"Phi-4-mini","provider":"Microsoft","rawName":"microsoft/Phi-4-mini-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.836B params","score":29.41,"unit":"%","rank":1121,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-32b","modelName":"Qwen1.5-32B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-32B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 32.512B params","score":29.26,"unit":"%","rank":1145,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-5-mini","modelName":"Phi-3.5-mini","provider":"Microsoft","rawName":"microsoft/Phi-3.5-mini-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.821B params","score":28.18,"unit":"%","rank":1276,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-mamba-7b-instruct","modelName":"Falcon3-Mamba-7B-Instruct","provider":"TII","rawName":"tiiuae/Falcon3-Mamba-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.273B params","score":28.11,"unit":"%","rank":1282,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-7b","modelName":"Qwen2.5-Coder (7B)","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":28.05,"unit":"%","rank":1287,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-7b","modelName":"Qwen2-7B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":27.94,"unit":"%","rank":1305,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-llama-70b","modelName":"DeepSeek-R1-Distill-Llama-70B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 70.554B params","score":27.81,"unit":"%","rank":1320,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-10b-base","modelName":"Falcon3-10B-Base","provider":"TII","rawName":"tiiuae/Falcon3-10B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 10.306B params","score":27.62,"unit":"%","rank":1334,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-mini-3-8b","modelName":"phi-3-mini 3.8B","provider":"Microsoft","rawName":"microsoft/Phi-3-mini-4k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 3.821B params","score":27.56,"unit":"%","rank":1339,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nous-hermes-2-mixtral-8x7b-dpo","modelName":"nous-hermes-2-mixtral-8x7b-dpo","provider":"NousResearch","rawName":"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 46.703B params","score":27.35,"unit":"%","rank":1357,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-llm-67b","modelName":"DeepSeek LLM 67B","provider":"DeepSeek","rawName":"deepseek-ai/deepseek-llm-67b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 67B params","score":27.31,"unit":"%","rank":1360,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-small-24b-base-2501","modelName":"Mistral-Small-24B-Base-2501","provider":"Mistral AI","rawName":"mistralai/Mistral-Small-24B-Base-2501","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 23.572B params","score":27.2,"unit":"%","rank":1370,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-3b","modelName":"Qwen2.5-3B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-3B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3B params","score":27.16,"unit":"%","rank":1378,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"exaone-3-5-2-4b-instruct","modelName":"EXAONE-3.5-2.4B-Instruct","provider":"LGAI-EXAONE","rawName":"LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.405B params","score":27.14,"unit":"%","rank":1379,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-3b-instruct","modelName":"Falcon3-3B-Instruct","provider":"TII UAE","rawName":"tiiuae/Falcon3-3B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.228B params","score":26.6,"unit":"%","rank":1433,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-vl-7b-instruct","modelName":"qwen2-vl-7b-instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-VL-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.291B params","score":26.49,"unit":"%","rank":1443,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-8b-dpo","modelName":"Llama-3.1-Tulu-3-8B-DPO","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-8B-DPO","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8B params","score":26.46,"unit":"%","rank":1446,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-3-mini-3-8b","modelName":"phi-3-mini 3.8B","provider":"Microsoft","rawName":"microsoft/Phi-3-mini-128k-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.821B params","score":26.34,"unit":"%","rank":1459,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-small-instruct-2409","modelName":"Mistral-Small-Instruct-2409","provider":"Mistral AI","rawName":"mistralai/Mistral-Small-Instruct-2409","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 22.05B params","score":26.26,"unit":"%","rank":1470,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-8b","modelName":"llama-3.1-tulu-3-8b","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-8B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.03B params","score":26.26,"unit":"%","rank":1471,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-8b","modelName":"llama-3.1-tulu-3-8b","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-8B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":26.03,"unit":"%","rank":1500,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"c4ai-command-r-v01","modelName":"c4ai-command-r-v01","provider":"Cohere","rawName":"CohereForAI/c4ai-command-r-v01","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 34.981B params","score":25.93,"unit":"%","rank":1516,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"exaone-3-0-7-8b-instruct","modelName":"EXAONE-3.0-7.8B-Instruct","provider":"LGAI-EXAONE","rawName":"LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.8B params","score":25.73,"unit":"%","rank":1546,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dbrx","modelName":"DBRX","provider":"Databricks","rawName":"databricks/dbrx-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 131.597B params","score":25.2,"unit":"%","rank":1607,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-14b","modelName":"Qwen2.5-Coder-14B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-14B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.77B params","score":24.83,"unit":"%","rank":1651,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-2-theta-llama-3-8b","modelName":"Hermes-2-Theta-Llama-3-8B","provider":"NousResearch","rawName":"NousResearch/Hermes-2-Theta-Llama-3-8B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":24.79,"unit":"%","rank":1657,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aya-23-35b","modelName":"aya-23-35B","provider":"Cohere","rawName":"CohereForAI/aya-23-35B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 34.981B params","score":24.76,"unit":"%","rank":1661,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-7b-base","modelName":"Falcon3-7B-Base","provider":"TII","rawName":"tiiuae/Falcon3-7B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.456B params","score":24.75,"unit":"%","rank":1665,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-nemo","modelName":"Mistral NeMo","provider":"Mistral AI","rawName":"mistralai/Mistral-Nemo-Instruct-2407","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 12.248B params","score":24.67,"unit":"%","rank":1676,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-34b","modelName":"Yi-34B","provider":"01.AI","rawName":"01-ai/Yi-34B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 34.389B params","score":24.23,"unit":"%","rank":1759,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-2-3b","modelName":"Llama-3.2-3B-Instruct","provider":"Meta","rawName":"meta-llama/Llama-3.2-3B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.213B params","score":24.2,"unit":"%","rank":1768,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"ministral-8b","modelName":"Ministral 8B","provider":"Mistral AI","rawName":"mistralai/Ministral-8B-Instruct-2410","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.02B params","score":24.19,"unit":"%","rank":1776,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-8b-instruct","modelName":"granite-3.0-8b-instruct","provider":"IBM","rawName":"ibm-granite/granite-3.0-8b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.171B params","score":24.03,"unit":"%","rank":1825,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-8b","modelName":"Llama 3-8B","provider":"Meta","rawName":"meta-llama/Meta-Llama-3-8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":23.91,"unit":"%","rank":1868,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mixtral-8x7b","modelName":"Mixtral 8x7B","provider":"Mistral AI","rawName":"mistralai/Mixtral-8x7B-Instruct-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 46.703B params","score":23.82,"unit":"%","rank":1884,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-8b","modelName":"Llama 3.1-8B","provider":"Meta","rawName":"meta-llama/Llama-3.1-8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.03B params","score":23.76,"unit":"%","rank":1905,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-nemo-minitron-8b-instruct","modelName":"Mistral-NeMo-Minitron-8B-Instruct","provider":"NVIDIA","rawName":"nvidia/Mistral-NeMo-Minitron-8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.414B params","score":23.57,"unit":"%","rank":1949,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-14b","modelName":"Qwen1.5-14B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-14B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.167B params","score":23.57,"unit":"%","rank":1952,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-3-llama-3-1-8b","modelName":"Hermes-3-Llama-3.1-8B","provider":"NousResearch","rawName":"NousResearch/Hermes-3-Llama-3.1-8B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":23.49,"unit":"%","rank":1976,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nous-hermes-2-solar-10-7b","modelName":"Nous-Hermes-2-SOLAR-10.7B","provider":"NousResearch","rawName":"NousResearch/Nous-Hermes-2-SOLAR-10.7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 10.732B params","score":23.41,"unit":"%","rank":2003,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"codestral-22b-v0-1","modelName":"Codestral-22B-v0.1","provider":"Mistral AI","rawName":"mistralai/Codestral-22B-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 22.247B params","score":23.28,"unit":"%","rank":2028,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-32b","modelName":"DeepSeek-R1-Distill-Qwen-32B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 32.764B params","score":22.96,"unit":"%","rank":2100,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stable-beluga-2","modelName":"Stable Beluga 2","provider":"Stability AI","rawName":"stabilityai/StableBeluga2","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 68.977B params","score":22.81,"unit":"%","rank":2129,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-1-5-6b-chat","modelName":"Yi-1.5-6B-Chat","provider":"01.AI","rawName":"01-ai/Yi-1.5-6B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.061B params","score":22.78,"unit":"%","rank":2136,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-8b-sft","modelName":"Llama-3.1-Tulu-3-8B-SFT","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-8B-SFT","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":22.6,"unit":"%","rank":2187,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-coder-7b","modelName":"Qwen2.5-Coder (7B)","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Coder-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7.616B params","score":22.52,"unit":"%","rank":2198,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aya-expanse-8b","modelName":"Aya-Expanse-8B","provider":"Cohere","rawName":"CohereForAI/aya-expanse-8b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.028B params","score":22.41,"unit":"%","rank":2218,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-1-5-9b","modelName":"Yi-1.5-9B","provider":"01.AI","rawName":"01-ai/Yi-1.5-9B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.829B params","score":22.15,"unit":"%","rank":2256,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-2-pro-llama-3-8b","modelName":"Hermes-2-Pro-Llama-3-8B","provider":"NousResearch","rawName":"NousResearch/Hermes-2-Pro-Llama-3-8B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.031B params","score":22.07,"unit":"%","rank":2269,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nous-hermes-2-mixtral-8x7b-sft","modelName":"Nous-Hermes-2-Mixtral-8x7B-SFT","provider":"NousResearch","rawName":"NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 46.703B params","score":21.84,"unit":"%","rank":2302,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-2-pro-mistral-7b","modelName":"Hermes-2-Pro-Mistral-7B","provider":"NousResearch","rawName":"NousResearch/Hermes-2-Pro-Mistral-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.242B params","score":21.84,"unit":"%","rank":2303,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmo-2-1124-7b-instruct","modelName":"OLMo-2-1124-7B-Instruct","provider":"Ai2","rawName":"allenai/OLMo-2-1124-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7.299B params","score":21.79,"unit":"%","rank":2324,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-math-7b-instruct","modelName":"Qwen2.5-Math-7B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Math-7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":21.77,"unit":"%","rank":2330,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-2b-instruct","modelName":"Granite-3.1-2B-Instruct","provider":"IBM","rawName":"ibm-granite/granite-3.1-2b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.534B params","score":21.71,"unit":"%","rank":2341,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-8b-base","modelName":"Granite-3.0-8B-Base","provider":"IBM","rawName":"ibm-granite/granite-3.0-8b-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.171B params","score":21.69,"unit":"%","rank":2349,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"openhermes-2-mistral-7b","modelName":"OpenHermes-2-Mistral-7B","provider":"teknium","rawName":"teknium/OpenHermes-2-Mistral-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":21.44,"unit":"%","rank":2405,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"openhermes-2-5-mistral-7b","modelName":"openhermes-2.5-mistral-7b","provider":"teknium","rawName":"teknium/OpenHermes-2.5-Mistral-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.242B params","score":21.32,"unit":"%","rank":2437,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-2-2b-instruct","modelName":"granite-3.2-2b-instruct","provider":"IBM","rawName":"ibm-granite/granite-3.2-2b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.534B params","score":21.25,"unit":"%","rank":2449,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nous-hermes-2-mistral-7b-dpo","modelName":"Nous-Hermes-2-Mistral-7B-DPO","provider":"NousResearch","rawName":"NousResearch/Nous-Hermes-2-Mistral-7B-DPO","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.242B params","score":21.1,"unit":"%","rank":2471,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-8b","modelName":"Llama 3-8B","provider":"Meta","rawName":"meta-llama/Meta-Llama-3-8B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.03B params","score":20.61,"unit":"%","rank":2570,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"solar-10-7b-instruct-v1-0","modelName":"solar-10.7b-instruct-v1.0","provider":"upstage","rawName":"upstage/SOLAR-10.7B-Instruct-v1.0","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 10.732B params","score":20.57,"unit":"%","rank":2576,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"glm-4-9b-chat-hf","modelName":"glm-4-9b-chat-hf","provider":"Zhipu AI (Z.ai)","rawName":"THUDM/glm-4-9b-chat-hf","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9.4B params","score":20.54,"unit":"%","rank":2584,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"acemath-1-5b-instruct","modelName":"AceMath-1.5B-Instruct","provider":"NVIDIA","rawName":"nvidia/AceMath-1.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.777B params","score":20.19,"unit":"%","rank":2653,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-8b-base","modelName":"Granite-3.1-8B-Base","provider":"IBM","rawName":"ibm-granite/granite-3.1-8b-base","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.171B params","score":20.06,"unit":"%","rank":2672,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mixtral-8x7b","modelName":"Mixtral 8x7B","provider":"Mistral AI","rawName":"mistralai/Mixtral-8x7B-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 46.703B params","score":19.67,"unit":"%","rank":2741,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-7b-v0-3","modelName":"Mistral 7B v0.3","provider":"Mistral AI","rawName":"mistralai/Mistral-7B-Instruct-v0.3","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.248B params","score":19.23,"unit":"%","rank":2799,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"recurrentgemma-9b-it","modelName":"recurrentgemma-9b-it","provider":"Google","rawName":"google/recurrentgemma-9b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9B params","score":19.22,"unit":"%","rank":2802,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-8b-sfr-iterative-dpo-r","modelName":"LLaMA-3-8B-SFR-Iterative-DPO-R","provider":"Salesforce","rawName":"Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-R","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":18.53,"unit":"%","rank":2882,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-7b-v0-2","modelName":"Mistral 7B v0.2","provider":"Mistral AI","rawName":"mistralai/Mistral-7B-Instruct-v0.2","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.242B params","score":18.51,"unit":"%","rank":2886,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"orca-2-13b","modelName":"Orca-2-13b","provider":"Microsoft","rawName":"microsoft/Orca-2-13b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13B params","score":18.5,"unit":"%","rank":2887,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-1-5b","modelName":"Qwen2.5-1.5B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-1.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.5B params","score":18.43,"unit":"%","rank":2895,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-2b-instruct","modelName":"granite-3.0-2b-instruct","provider":"IBM","rawName":"ibm-granite/granite-3.0-2b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.634B params","score":18.4,"unit":"%","rank":2899,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-2-70b","modelName":"Llama 2-70B","provider":"Meta","rawName":"meta-llama/Llama-2-70b-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 68.977B params","score":18.37,"unit":"%","rank":2905,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nemotron-mini-4b-instruct","modelName":"Nemotron-Mini-4B-Instruct","provider":"NVIDIA","rawName":"nvidia/Nemotron-Mini-4B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 4B params","score":18.36,"unit":"%","rank":2906,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-mamba-7b-base","modelName":"Falcon3-Mamba-7B-Base","provider":"TII","rawName":"tiiuae/Falcon3-Mamba-7B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.273B params","score":18.14,"unit":"%","rank":2930,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aceinstruct-1-5b","modelName":"AceInstruct-1.5B","provider":"NVIDIA","rawName":"nvidia/AceInstruct-1.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.777B params","score":18.12,"unit":"%","rank":2937,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-3b","modelName":"Qwen2.5-3B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-3B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.086B params","score":18.1,"unit":"%","rank":2940,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"glm-4-9b","modelName":"GLM-4-9B","provider":"Zhipu AI (Z.ai)","rawName":"THUDM/glm-4-9b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9B params","score":18.01,"unit":"%","rank":2952,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-7b","modelName":"internlm2-7b","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2-7b","variant":"average","setting":"Average of 6 normalised benchmarks; float16","score":17.92,"unit":"%","rank":2961,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-math-7b","modelName":"Qwen2.5-Math-7B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Math-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":17.84,"unit":"%","rank":2969,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-9b","modelName":"Yi-9B","provider":"01.AI","rawName":"01-ai/Yi-9B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.829B params","score":17.81,"unit":"%","rank":2972,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-nemo-minitron-8b-base","modelName":"Mistral-NeMo-Minitron-8B-Base","provider":"NVIDIA","rawName":"nvidia/Mistral-NeMo-Minitron-8B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.88B params","score":17.7,"unit":"%","rank":2988,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-1-1-7b-it","modelName":"gemma-1.1-7b-it","provider":"Google","rawName":"google/gemma-1.1-7b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.538B params","score":17.69,"unit":"%","rank":2989,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-7b","modelName":"Qwen1.5-7B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-7B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.721B params","score":17.62,"unit":"%","rank":2993,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmoe-1b-7b-0125-instruct","modelName":"OLMoE-1B-7B-0125-Instruct","provider":"Ai2","rawName":"allenai/OLMoE-1B-7B-0125-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 6.919B params","score":17.51,"unit":"%","rank":3008,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"decilm-7b-instruct","modelName":"DeciLM-7B-instruct","provider":"Deci","rawName":"Deci/DeciLM-7B-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.044B params","score":17.47,"unit":"%","rank":3013,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-3b-a800m-instruct","modelName":"Granite-3.1-3B-A800M-Instruct","provider":"IBM","rawName":"ibm-granite/granite-3.1-3b-a800m-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 3.299B params","score":17.28,"unit":"%","rank":3035,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-2b-jpn-it","modelName":"gemma-2-2b-jpn-it","provider":"Google","rawName":"google/gemma-2-2b-jpn-it","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.614B params","score":17.12,"unit":"%","rank":3056,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-2b-it","modelName":"Gemma-2-2B-it","provider":"Google","rawName":"google/gemma-2-2b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.614B params","score":17.05,"unit":"%","rank":3062,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-coder-9b-chat","modelName":"Yi-Coder-9B-Chat","provider":"01.AI","rawName":"01-ai/Yi-Coder-9B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.829B params","score":16.99,"unit":"%","rank":3068,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"solar-10-7b-v1-0","modelName":"SOLAR-10.7B-v1.0","provider":"upstage","rawName":"upstage/SOLAR-10.7B-v1.0","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 10.732B params","score":16.85,"unit":"%","rank":3078,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-2-12b-chat","modelName":"stablelm-2-12b-chat","provider":"stabilityai","rawName":"stabilityai/stablelm-2-12b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 12.143B params","score":16.78,"unit":"%","rank":3089,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-1-5-6b","modelName":"Yi-1.5-6B","provider":"01.AI","rawName":"01-ai/Yi-1.5-6B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.061B params","score":16.75,"unit":"%","rank":3096,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-2b-jpn-it","modelName":"gemma-2-2b-jpn-it","provider":"Google","rawName":"google/gemma-2-2b-jpn-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.614B params","score":16.68,"unit":"%","rank":3106,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dbrx","modelName":"DBRX","provider":"Databricks","rawName":"databricks/dbrx-base","variant":"average","setting":"Average of 6 normalised benchmarks; float16","score":16.36,"unit":"%","rank":3156,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-1b-instruct","modelName":"Falcon3-1B-Instruct","provider":"TII UAE","rawName":"tiiuae/Falcon3-1B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.669B params","score":16.16,"unit":"%","rank":3179,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"aya-23-8b","modelName":"aya-23-8B","provider":"Cohere","rawName":"CohereForAI/aya-23-8B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.028B params","score":16.01,"unit":"%","rank":3193,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-moe-a2-7b-chat","modelName":"Qwen1.5-MoE-A2.7B-Chat","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-MoE-A2.7B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.316B params","score":15.88,"unit":"%","rank":3215,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-3b-base","modelName":"Falcon3-3B-Base","provider":"TII","rawName":"tiiuae/Falcon3-3B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.228B params","score":15.74,"unit":"%","rank":3227,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yarn-solar-10b","modelName":"Yarn-Solar-10b-32k","provider":"NousResearch","rawName":"NousResearch/Yarn-Solar-10b-32k","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 10B params","score":15.72,"unit":"%","rank":3228,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-2","modelName":"Phi-2","provider":"Microsoft","rawName":"microsoft/phi-2","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.78B params","score":15.53,"unit":"%","rank":3250,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-7b","modelName":"Gemma 7B","provider":"Google","rawName":"google/gemma-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.538B params","score":15.44,"unit":"%","rank":3260,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hermes-3-llama-3-2-3b","modelName":"Hermes-3-Llama-3.2-3B","provider":"NousResearch","rawName":"NousResearch/Hermes-3-Llama-3.2-3B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.213B params","score":15.24,"unit":"%","rank":3275,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-nemo","modelName":"Mistral NeMo","provider":"Mistral AI","rawName":"mistralai/Mistral-Nemo-Base-2407","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 11.58B params","score":15.24,"unit":"%","rank":3276,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon-mamba-7b","modelName":"falcon-mamba-7b","provider":"TII","rawName":"tiiuae/falcon-mamba-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":15.18,"unit":"%","rank":3281,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"glm-4-9b-chat-1m-hf","modelName":"glm-4-9b-chat-1m-hf","provider":"Zhipu AI (Z.ai)","rawName":"THUDM/glm-4-9b-chat-1m-hf","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9.484B params","score":15.14,"unit":"%","rank":3289,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"decilm-7b","modelName":"DeciLM-7B","provider":"Deci","rawName":"Deci/DeciLM-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.044B params","score":15.02,"unit":"%","rank":3304,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-1-7b-instruct","modelName":"smollm2-1.7b-instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-1.7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.711B params","score":15.02,"unit":"%","rank":3305,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-7b","modelName":"DeepSeek-R1-Distill-Qwen-7B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":14.99,"unit":"%","rank":3310,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-llm-7b","modelName":"deepseek-llm-7b-chat","provider":"DeepSeek","rawName":"deepseek-ai/deepseek-llm-7b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":14.82,"unit":"%","rank":3321,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-5-1-8b-chat","modelName":"internlm2_5-1_8b-chat","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2_5-1_8b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.89B params","score":14.75,"unit":"%","rank":3329,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mistral-7b-v0-1","modelName":"Mistral 7B v0.1","provider":"Mistral AI","rawName":"mistralai/Mistral-7B-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.242B params","score":14.58,"unit":"%","rank":3352,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-2-1b","modelName":"Llama 3.2 1B","provider":"Meta","rawName":"meta-llama/Llama-3.2-1B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.24B params","score":14.44,"unit":"%","rank":3366,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"orca-2-7b","modelName":"Orca-2-7b","provider":"Microsoft","rawName":"microsoft/Orca-2-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":14.4,"unit":"%","rank":3370,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"collectivecognition-v1-1-mistral-7b","modelName":"CollectiveCognition-v1.1-Mistral-7B","provider":"teknium","rawName":"teknium/CollectiveCognition-v1.1-Mistral-7B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7B params","score":14.26,"unit":"%","rank":3385,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"minitron-8b-base","modelName":"Minitron-8B-Base","provider":"NVIDIA","rawName":"nvidia/Minitron-8B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.22B params","score":14.22,"unit":"%","rank":3392,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hymba-1-5b-instruct","modelName":"Hymba-1.5B-Instruct","provider":"NVIDIA","rawName":"nvidia/Hymba-1.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.523B params","score":14.19,"unit":"%","rank":3395,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-1-5b-instruct","modelName":"Qwen2-1.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-1.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.544B params","score":14.14,"unit":"%","rank":3404,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yi-6b","modelName":"Yi 6B","provider":"01.AI","rawName":"01-ai/Yi-6B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.061B params","score":14.12,"unit":"%","rank":3406,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dclm-7b","modelName":"DCLM-7B","provider":"apple","rawName":"apple/DCLM-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":14.11,"unit":"%","rank":3407,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-2b-base","modelName":"Granite-3.0-2B-Base","provider":"IBM","rawName":"ibm-granite/granite-3.0-2b-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.634B params","score":14.1,"unit":"%","rank":3408,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-2-12b","modelName":"stablelm-2-12b","provider":"stabilityai","rawName":"stabilityai/stablelm-2-12b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 12.143B params","score":14,"unit":"%","rank":3417,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-moe-a2-7b","modelName":"Qwen1.5-MoE-A2.7B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-MoE-A2.7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 14.316B params","score":13.95,"unit":"%","rank":3427,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon-2-11b","modelName":"Falcon 2 11B","provider":"Technology Innovation Institute","rawName":"tiiuae/falcon-11B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 11.103B params","score":13.85,"unit":"%","rank":3439,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"recurrentgemma-9b","modelName":"recurrentgemma-9b","provider":"Google","rawName":"google/recurrentgemma-9b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9B params","score":13.71,"unit":"%","rank":3452,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmoe-1b-7b-0924-instruct","modelName":"OLMoE-1B-7B-0924-Instruct","provider":"Ai2","rawName":"allenai/OLMoE-1B-7B-0924-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.919B params","score":13.7,"unit":"%","rank":3453,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-3b-a800m-instruct","modelName":"granite-3.0-3b-a800m-instruct","provider":"IBM","rawName":"ibm-granite/granite-3.0-3b-a800m-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.374B params","score":13.7,"unit":"%","rank":3454,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-ul2","modelName":"flan-ul2","provider":"Google","rawName":"google/flan-ul2","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 19.46B params","score":13.68,"unit":"%","rank":3458,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-xxl","modelName":"flan-t5-xxl","provider":"Google","rawName":"google/flan-t5-xxl","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 11.267B params","score":13.66,"unit":"%","rank":3460,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yarn-mistral-7b","modelName":"Yarn-Mistral-7b-64k","provider":"NousResearch","rawName":"NousResearch/Yarn-Mistral-7b-64k","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":13.54,"unit":"%","rank":3471,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-2b-base","modelName":"Granite-3.1-2B-Base","provider":"IBM","rawName":"ibm-granite/granite-3.1-2b-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.534B params","score":13.2,"unit":"%","rank":3500,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-7b-it","modelName":"gemma-7b-it","provider":"Google","rawName":"google/gemma-7b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.538B params","score":13.07,"unit":"%","rank":3506,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-llama-8b","modelName":"DeepSeek-R1-Distill-Llama-8B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8.03B params","score":13.06,"unit":"%","rank":3507,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"openmath2-llama3-1-8b","modelName":"OpenMath2-Llama3.1-8B","provider":"NVIDIA","rawName":"nvidia/OpenMath2-Llama3.1-8B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 8.03B params","score":12.75,"unit":"%","rank":3525,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-4b-chat","modelName":"qwen1.5-4b-chat","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-4B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.95B params","score":12.63,"unit":"%","rank":3532,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-zephyr-3b","modelName":"stablelm-zephyr-3b","provider":"stabilityai","rawName":"stabilityai/stablelm-zephyr-3b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.795B params","score":12.37,"unit":"%","rank":3557,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwq-32b","modelName":"QwQ-32B","provider":"Alibaba (Qwen)","rawName":"Qwen/QwQ-32B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 32.764B params","score":12.21,"unit":"%","rank":3574,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"openhermes-13b","modelName":"OpenHermes-13B","provider":"teknium","rawName":"teknium/OpenHermes-13B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13B params","score":12.18,"unit":"%","rank":3575,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-7b-instruct","modelName":"granite-7b-instruct","provider":"IBM","rawName":"ibm-granite/granite-7b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.738B params","score":12.03,"unit":"%","rank":3587,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-math-1-5b-instruct","modelName":"Qwen2.5-Math-1.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-Math-1.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.544B params","score":12.02,"unit":"%","rank":3588,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-math-7b","modelName":"Qwen2-Math-7B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-Math-7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.616B params","score":12.02,"unit":"%","rank":3591,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"minitron-4b-base","modelName":"Minitron-4B-Base","provider":"NVIDIA","rawName":"nvidia/Minitron-4B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 4B params","score":11.98,"unit":"%","rank":3598,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-4b","modelName":"Qwen1.5-4B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-4B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.95B params","score":11.77,"unit":"%","rank":3616,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-xl","modelName":"flan-t5-xl","provider":"Google","rawName":"google/flan-t5-xl","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.85B params","score":11.71,"unit":"%","rank":3619,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-minitron-4b-depth-base","modelName":"Llama-3.1-Minitron-4B-Depth-Base","provider":"NVIDIA","rawName":"nvidia/Llama-3.1-Minitron-4B-Depth-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 4.02B params","score":11.66,"unit":"%","rank":3624,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-xl","modelName":"flan-t5-xl","provider":"Google","rawName":"google/flan-t5-xl","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.85B params","score":11.59,"unit":"%","rank":3633,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon-40b","modelName":"Falcon-40B","provider":"Technology Innovation Institute","rawName":"tiiuae/falcon-40b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 40B params","score":11.4,"unit":"%","rank":3643,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-2-13b-chat-hf","modelName":"Llama-2-13b-chat-hf","provider":"Meta","rawName":"meta-llama/Llama-2-13b-chat-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 13.016B params","score":11.13,"unit":"%","rank":3660,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-2-13b-hf","modelName":"Llama-2-13b-hf","provider":"Meta","rawName":"meta-llama/Llama-2-13b-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 13.016B params","score":11.07,"unit":"%","rank":3665,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"glm-4-9b-chat","modelName":"GLM-4-9B-Chat","provider":"Zhipu AI (Z.ai)","rawName":"THUDM/glm-4-9b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9B params","score":10.97,"unit":"%","rank":3670,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmo-7b-instruct-hf","modelName":"OLMo-7B-Instruct-hf","provider":"Ai2","rawName":"allenai/OLMo-7B-Instruct-hf","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":10.85,"unit":"%","rank":3684,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-chat-1-8b","modelName":"internlm2-chat-1_8b","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2-chat-1_8b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.889B params","score":10.64,"unit":"%","rank":3694,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-1-5b","modelName":"Qwen2-1.5B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-1.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.544B params","score":10.45,"unit":"%","rank":3703,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-2b","modelName":"gemma-2-2b","provider":"Google","rawName":"google/gemma-2-2b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.614B params","score":10.36,"unit":"%","rank":3709,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-1-5b","modelName":"DeepSeek-R1-Distill-Qwen-1.5B","provider":"DeepSeek","rawName":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.777B params","score":10.35,"unit":"%","rank":3710,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-moe-16b-chat","modelName":"deepseek-moe-16b-chat","provider":"DeepSeek","rawName":"deepseek-ai/deepseek-moe-16b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 16.376B params","score":10.29,"unit":"%","rank":3711,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2-2b","modelName":"gemma-2-2b","provider":"Google","rawName":"google/gemma-2-2b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.614B params","score":10.13,"unit":"%","rank":3720,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-1b-a400m-instruct","modelName":"Granite-3.1-1B-A400M-Instruct","provider":"IBM","rawName":"ibm-granite/granite-3.1-1b-a400m-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.335B params","score":10.13,"unit":"%","rank":3721,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-0-5b-instruct","modelName":"Qwen2.5-0.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-0.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.494B params","score":10.11,"unit":"%","rank":3723,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-3b-a800m-base","modelName":"Granite-3.1-3B-A800M-Base","provider":"IBM","rawName":"ibm-granite/granite-3.1-3b-a800m-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.299B params","score":10,"unit":"%","rank":3730,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon3-1b-base","modelName":"Falcon3-1B-Base","provider":"TII","rawName":"tiiuae/Falcon3-1B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.669B params","score":9.89,"unit":"%","rank":3734,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-large","modelName":"flan-t5-large","provider":"Google","rawName":"google/flan-t5-large","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.783B params","score":9.66,"unit":"%","rank":3744,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-2-7b-chat-hf","modelName":"Llama-2-7b-chat-hf","provider":"Meta","rawName":"meta-llama/Llama-2-7b-chat-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 6.738B params","score":9.61,"unit":"%","rank":3748,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-1-7b","modelName":"SmolLM2-1.7B","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-1.7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.71B params","score":9.58,"unit":"%","rank":3749,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"openhermes-7b","modelName":"OpenHermes-7B","provider":"teknium","rawName":"teknium/OpenHermes-7B","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7B params","score":9.57,"unit":"%","rank":3750,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-3b-a800m-base","modelName":"granite-3.0-3b-a800m-base","provider":"IBM","rawName":"ibm-granite/granite-3.0-3b-a800m-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.374B params","score":9.49,"unit":"%","rank":3757,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-2-zephyr-1-6b","modelName":"stablelm-2-zephyr-1_6b","provider":"stabilityai","rawName":"stabilityai/stablelm-2-zephyr-1_6b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.645B params","score":9.46,"unit":"%","rank":3759,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nous-hermes-llama-2-7b","modelName":"Nous-Hermes-llama-2-7b","provider":"NousResearch","rawName":"NousResearch/Nous-Hermes-llama-2-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.738B params","score":9.32,"unit":"%","rank":3767,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-1-8b","modelName":"Qwen1.5-1.8B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-1.8B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.837B params","score":9.27,"unit":"%","rank":3769,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-1-8b-chat","modelName":"Qwen1.5-1.8B-Chat","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-1.8B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.837B params","score":9.26,"unit":"%","rank":3770,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"jamba-v0-1","modelName":"Jamba-v0.1","provider":"ai21labs","rawName":"ai21labs/Jamba-v0.1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 51.57B params","score":9.22,"unit":"%","rank":3774,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"minicpm-s-1b-sft-llama-format","modelName":"MiniCPM-S-1B-sft-llama-format","provider":"openbmb","rawName":"openbmb/MiniCPM-S-1B-sft-llama-format","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1B params","score":9,"unit":"%","rank":3784,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"glm-4-9b-chat-1m","modelName":"glm-4-9b-chat-1m","provider":"Zhipu AI (Z.ai)","rawName":"THUDM/glm-4-9b-chat-1m","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 9.484B params","score":8.92,"unit":"%","rank":3787,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-2-1-6b-chat","modelName":"stablelm-2-1_6b-chat","provider":"stabilityai","rawName":"stabilityai/stablelm-2-1_6b-chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.645B params","score":8.87,"unit":"%","rank":3793,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-2-7b-hf","modelName":"Llama-2-7b-hf","provider":"Meta","rawName":"meta-llama/Llama-2-7b-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 6.738B params","score":8.81,"unit":"%","rank":3798,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"internlm2-1-8b","modelName":"internlm2-1_8b","provider":"Shanghai AI Lab (InternLM)","rawName":"internlm/internlm2-1_8b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8B params","score":8.75,"unit":"%","rank":3802,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yarn-llama-2-13b","modelName":"Yarn-Llama-2-13b-128k","provider":"NousResearch","rawName":"NousResearch/Yarn-Llama-2-13b-128k","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13B params","score":8.49,"unit":"%","rank":3826,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"nexusraven-v2-13b","modelName":"NexusRaven-V2-13B","provider":"Nexusflow","rawName":"Nexusflow/NexusRaven-V2-13B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 13B params","score":8.49,"unit":"%","rank":3827,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-0-5b-instruct","modelName":"Qwen2.5-0.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-0.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.5B params","score":8.14,"unit":"%","rank":3860,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-360m-instruct","modelName":"SmolLM2-360M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-360M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.36B params","score":8.14,"unit":"%","rank":3861,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-1b-a400m-instruct","modelName":"granite-3.0-1b-a400m-instruct","provider":"IBM","rawName":"ibm-granite/granite-3.0-1b-a400m-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.335B params","score":8.07,"unit":"%","rank":3874,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-1-1-2b-it","modelName":"gemma-1.1-2b-it","provider":"Google","rawName":"google/gemma-1.1-2b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.506B params","score":8.05,"unit":"%","rank":3878,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"hymba-1-5b-base","modelName":"Hymba-1.5B-Base","provider":"NVIDIA","rawName":"nvidia/Hymba-1.5B-Base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.523B params","score":8.04,"unit":"%","rank":3883,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"recurrentgemma-2b-it","modelName":"recurrentgemma-2b-it","provider":"Google","rawName":"google/recurrentgemma-2b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.683B params","score":8,"unit":"%","rank":3888,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-7b-base","modelName":"granite-7b-base","provider":"IBM","rawName":"ibm-granite/granite-7b-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.738B params","score":7.91,"unit":"%","rank":3898,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2b-it","modelName":"gemma-2b-it","provider":"Google","rawName":"google/gemma-2b-it","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.506B params","score":7.49,"unit":"%","rank":4002,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"deepseek-moe-16b-base","modelName":"deepseek-moe-16b-base","provider":"DeepSeek","rawName":"deepseek-ai/deepseek-moe-16b-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 16.376B params","score":7.47,"unit":"%","rank":4005,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-3b-4e1t","modelName":"stablelm-3b-4e1t","provider":"stabilityai","rawName":"stabilityai/stablelm-3b-4e1t","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.795B params","score":7.33,"unit":"%","rank":4026,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gemma-2b","modelName":"Gemma 2B","provider":"Google","rawName":"google/gemma-2b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.506B params","score":7.32,"unit":"%","rank":4027,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmoe-1b-7b-0924","modelName":"OLMoE-1B-7B-0924","provider":"Ai2","rawName":"allenai/OLMoE-1B-7B-0924","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.919B params","score":7.27,"unit":"%","rank":4035,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-0-5b","modelName":"Qwen2-0.5B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-0.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.494B params","score":7.22,"unit":"%","rank":4037,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"yarn-llama-2-7b","modelName":"Yarn-Llama-2-7b-64k","provider":"NousResearch","rawName":"NousResearch/Yarn-Llama-2-7b-64k","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":7.22,"unit":"%","rank":4041,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-1-5","modelName":"Phi-1.5","provider":"Microsoft","rawName":"microsoft/phi-1_5","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.418B params","score":7.17,"unit":"%","rank":4043,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"codegemma-1-1-2b","modelName":"codegemma-1.1-2b","provider":"Google","rawName":"google/codegemma-1.1-2b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.506B params","score":7.13,"unit":"%","rank":4047,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"recurrentgemma-2b","modelName":"recurrentgemma-2b","provider":"Google","rawName":"google/recurrentgemma-2b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.683B params","score":7.02,"unit":"%","rank":4058,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dolly-v1-6b","modelName":"dolly-v1-6b","provider":"databricks","rawName":"databricks/dolly-v1-6b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6B params","score":6.98,"unit":"%","rank":4061,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-135m","modelName":"SmolLM-135M","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-135M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.13B params","score":6.95,"unit":"%","rank":4065,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmo-7b-hf","modelName":"OLMo-7B-hf","provider":"Ai2","rawName":"allenai/OLMo-7B-hf","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6.888B params","score":6.86,"unit":"%","rank":4078,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmo-1b-hf","modelName":"OLMo-1B-hf","provider":"Ai2","rawName":"allenai/OLMo-1B-hf","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.177B params","score":6.63,"unit":"%","rank":4095,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-0-5b-instruct","modelName":"Qwen2-0.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2-0.5B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.494B params","score":6.59,"unit":"%","rank":4104,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gpt-j-6b","modelName":"GPT-J-6B","provider":"EleutherAI","rawName":"EleutherAI/gpt-j-6b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 6B params","score":6.57,"unit":"%","rank":4107,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen2-5-0-5b","modelName":"Qwen2.5-0.5B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen2.5-0.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.5B params","score":6.55,"unit":"%","rank":4110,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-135m-instruct","modelName":"SmolLM2-135M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-135M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.135B params","score":6.47,"unit":"%","rank":4116,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gpt-neo-2-7b","modelName":"GPT-Neo-2.7B","provider":"EleutherAI","rawName":"EleutherAI/gpt-neo-2.7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 2.718B params","score":6.43,"unit":"%","rank":4119,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-base","modelName":"flan-t5-base","provider":"Google","rawName":"google/flan-t5-base","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.248B params","score":6.42,"unit":"%","rank":4122,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dolly-2-0-12b","modelName":"Dolly 2.0-12b","provider":"Databricks","rawName":"databricks/dolly-v2-12b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 12B params","score":6.37,"unit":"%","rank":4126,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-1-1b-a400m-base","modelName":"Granite-3.1-1B-A400M-Base","provider":"IBM","rawName":"ibm-granite/granite-3.1-1b-a400m-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.335B params","score":6.31,"unit":"%","rank":4133,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-360m","modelName":"SmolLM-360M","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-360M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.36B params","score":6.26,"unit":"%","rank":4137,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-360m","modelName":"SmolLM2-360M","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-360M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.36B params","score":6.25,"unit":"%","rank":4140,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"flan-t5-small","modelName":"flan-t5-small","provider":"Google","rawName":"google/flan-t5-small","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.077B params","score":6.13,"unit":"%","rank":4144,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gpt-neox-20b","modelName":"GPT-NeoX 20B","provider":"EleutherAI","rawName":"EleutherAI/gpt-neox-20b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 20.739B params","score":6.12,"unit":"%","rank":4145,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-12b","modelName":"pythia-12b","provider":"EleutherAI","rawName":"EleutherAI/pythia-12b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 12B params","score":6.06,"unit":"%","rank":4147,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mpt-7b","modelName":"MPT-7B","provider":"MosaicML","rawName":"mosaicml/mpt-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":6.03,"unit":"%","rank":4152,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"granite-3-0-1b-a400m-base","modelName":"granite-3.0-1b-a400m-base","provider":"IBM","rawName":"ibm-granite/granite-3.0-1b-a400m-base","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.335B params","score":6.03,"unit":"%","rank":4153,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-1-4b","modelName":"pythia-1.4b","provider":"EleutherAI","rawName":"EleutherAI/pythia-1.4b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.515B params","score":6.01,"unit":"%","rank":4154,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-6-9b","modelName":"pythia-6.9b","provider":"EleutherAI","rawName":"EleutherAI/pythia-6.9b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 6.9B params","score":5.97,"unit":"%","rank":4161,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-160m","modelName":"pythia-160m","provider":"EleutherAI","rawName":"EleutherAI/pythia-160m","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.213B params","score":5.73,"unit":"%","rank":4185,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-135m","modelName":"SmolLM2-135M","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-135M","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.135B params","score":5.7,"unit":"%","rank":4192,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-0-5b-chat","modelName":"Qwen1.5-0.5B-Chat","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-0.5B-Chat","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.62B params","score":5.68,"unit":"%","rank":4195,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dolly-v2-7b","modelName":"dolly-v2-7b","provider":"databricks","rawName":"databricks/dolly-v2-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":5.65,"unit":"%","rank":4199,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dolly-v2-3b","modelName":"dolly-v2-3b","provider":"databricks","rawName":"databricks/dolly-v2-3b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3B params","score":5.6,"unit":"%","rank":4201,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-1-7b","modelName":"SmolLM-1.7B","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-1.7B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.71B params","score":5.58,"unit":"%","rank":4205,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"phi-1","modelName":"phi-1","provider":"Microsoft","rawName":"microsoft/phi-1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.418B params","score":5.57,"unit":"%","rank":4206,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-2-8b","modelName":"pythia-2.8b","provider":"EleutherAI","rawName":"EleutherAI/pythia-2.8b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 2.909B params","score":5.55,"unit":"%","rank":4213,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-1-7b-instruct","modelName":"SmolLM-1.7B-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-1.7B-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.71B params","score":5.49,"unit":"%","rank":4223,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gpt-neo-1-3b","modelName":"gpt-neo-1.3B","provider":"EleutherAI","rawName":"EleutherAI/gpt-neo-1.3B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.366B params","score":5.39,"unit":"%","rank":4236,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"qwen1-5-0-5b","modelName":"Qwen1.5-0.5B","provider":"Alibaba (Qwen)","rawName":"Qwen/Qwen1.5-0.5B","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.62B params","score":5.35,"unit":"%","rank":4242,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"stablelm-2-1-6b","modelName":"stablelm-2-1_6b","provider":"stabilityai","rawName":"stabilityai/stablelm-2-1_6b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.645B params","score":5.32,"unit":"%","rank":4247,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"dialogpt","modelName":"DialoGPT-medium","provider":"Microsoft","rawName":"microsoft/DialoGPT-medium","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.345B params","score":5.25,"unit":"%","rank":4251,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-410m","modelName":"pythia-410m","provider":"EleutherAI","rawName":"EleutherAI/pythia-410m","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.506B params","score":5.23,"unit":"%","rank":4255,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mt5-xl","modelName":"mt5-xl","provider":"Google","rawName":"google/mt5-xl","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 3.23B params","score":5.19,"unit":"%","rank":4263,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon-7b","modelName":"Falcon-7B","provider":"Technology Innovation Institute","rawName":"tiiuae/falcon-7b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":5.17,"unit":"%","rank":4264,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"falcon-7b-instruct","modelName":"falcon-7b-instruct","provider":"TII","rawName":"tiiuae/falcon-7b-instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7B params","score":5.12,"unit":"%","rank":4275,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mt5-xxl","modelName":"mt5-xxl","provider":"Google","rawName":"google/mt5-xxl","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 11.9B params","score":5.1,"unit":"%","rank":4278,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"pythia-1b","modelName":"pythia-1b","provider":"EleutherAI","rawName":"EleutherAI/pythia-1b","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 1.079B params","score":5.07,"unit":"%","rank":4287,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-360m-instruct","modelName":"SmolLM-360M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-360M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.362B params","score":5.01,"unit":"%","rank":4296,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"gpt-neo-125m","modelName":"gpt-neo-125m","provider":"EleutherAI","rawName":"EleutherAI/gpt-neo-125m","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.15B params","score":4.41,"unit":"%","rank":4377,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"bloom-3b","modelName":"bloom-3b","provider":"bigscience","rawName":"bigscience/bloom-3b","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 3.003B params","score":4.39,"unit":"%","rank":4384,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mt5-small","modelName":"mt5-small","provider":"Google","rawName":"google/mt5-small","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.17B params","score":4.26,"unit":"%","rank":4404,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"llama-3-1-tulu-3-8b-rm","modelName":"Llama-3.1-Tulu-3-8B-RM","provider":"Ai2","rawName":"allenai/Llama-3.1-Tulu-3-8B-RM","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 8B params","score":4.24,"unit":"%","rank":4410,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"bloom-1b7","modelName":"bloom-1b7","provider":"bigscience","rawName":"bigscience/bloom-1b7","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.722B params","score":4.05,"unit":"%","rank":4435,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"bloom-1b1","modelName":"bloom-1b1","provider":"bigscience","rawName":"bigscience/bloom-1b1","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 1.065B params","score":4.03,"unit":"%","rank":4440,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"olmo-1-7-7b-hf","modelName":"OLMo-1.7-7B-hf","provider":"Ai2","rawName":"allenai/OLMo-1.7-7B-hf","variant":"average","setting":"Average of 6 normalised benchmarks; float16","score":3.8,"unit":"%","rank":4476,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"bloom-7b1","modelName":"bloom-7b1","provider":"bigscience","rawName":"bigscience/bloom-7b1","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 7.069B params","score":3.8,"unit":"%","rank":4477,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"mt5-base","modelName":"mt5-base","provider":"Google","rawName":"google/mt5-base","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.39B params","score":3.72,"unit":"%","rank":4486,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm-135m-instruct","modelName":"SmolLM-135M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM-135M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.135B params","score":3.65,"unit":"%","rank":4497,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"umt5-base","modelName":"umt5-base","provider":"Google","rawName":"google/umt5-base","variant":"average","setting":"Average of 6 normalised benchmarks; float16; -1B params","score":3.52,"unit":"%","rank":4523,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"bloom-560m","modelName":"bloom-560m","provider":"bigscience","rawName":"bigscience/bloom-560m","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 0.559B params","score":3.51,"unit":"%","rank":4525,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"acemath-72b-rm","modelName":"AceMath-72B-RM","provider":"NVIDIA","rawName":"nvidia/AceMath-72B-RM","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 71.461B params","score":3.43,"unit":"%","rank":4534,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"switch-base-8","modelName":"switch-base-8","provider":"Google","rawName":"google/switch-base-8","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.62B params","score":3.3,"unit":"%","rank":4545,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"acemath-7b-rm","modelName":"AceMath-7B-RM","provider":"NVIDIA","rawName":"nvidia/AceMath-7B-RM","variant":"average","setting":"Average of 6 normalised benchmarks; bfloat16; 7.071B params","score":3.22,"unit":"%","rank":4553,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-135m-instruct","modelName":"SmolLM2-135M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-135M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.135B params","score":3.21,"unit":"%","rank":4554,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"},{"model":"smollm2-360m-instruct","modelName":"SmolLM2-360M-Instruct","provider":"Hugging Face","rawName":"HuggingFaceTB/SmolLM2-360M-Instruct","variant":"average","setting":"Average of 6 normalised benchmarks; float16; 0.362B params","score":3.1,"unit":"%","rank":4562,"rankComputedBySite":false,"date":"2025-03-13","sourceType":"official","source":"openllm","sourceUrl":"https://huggingface.co/datasets/open-llm-leaderboard/contents","collected":"2026-10-10"}]}