{"source":"AIMap","schema":"benchmark/v1","updated":"2026-10-22","benchmark":{"id":"livecodebench","name":"LiveCodeBench","category":"coding","unit":"%","higherIsBetter":true,"status":"stale","sources":["livecodebench"],"primaryVariant":"codegen-2025","url":"https://livecodebench.github.io/leaderboard.html","year":2024,"desc":{"en":"Coding problems collected continuously from LeetCode, AtCoder and Codeforces with their release dates, so models can be scored only on problems published after their training cut-off.","zh-hans":"持续从 LeetCode、AtCoder、Codeforces 收集带发布日期的编程题，可以只用模型训练截止日之后的新题来评分。"},"measures":{"en":"pass@1 on code generation. We average the official per-problem results for problems dated 2025-01-01 or later.","zh-hans":"代码生成 pass@1。本站对官方逐题结果中 2025-01-01 及以后的题目求平均。"},"limits":{"en":"The public leaderboard file has not been updated since August 2025, so recent models are missing. Our window average can differ slightly from the site's default view.","zh-hans":"公开榜单文件自 2025 年 8 月起没有更新，缺少新模型；本站的时间窗平均值与官网默认视图可能略有差异。"},"contamination":"low","contaminationNote":{"en":"Time-windowed problems reduce contamination by design.","zh-hans":"按时间窗选题，设计上降低污染。"},"stats":{"results":22,"models":22,"latest":"2025-04-07","bySourceType":{"official":22}}},"sources":[{"id":"livecodebench","name":"LiveCodeBench leaderboard","license":"No explicit licence on the site repo (benchmark code MIT) – factual scores only, with citation","policy":"facts","attribution":"LiveCodeBench (Jain et al.), livecodebench.github.io","site":"https://livecodebench.github.io/leaderboard.html"}],"results":[{"model":"o4-mini","modelName":"o4-mini","provider":"OpenAI","rawName":"O4-Mini (High)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":75.8,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-2-5-pro-jun-2025","modelName":"Gemini 2.5 Pro (Jun 2025)","provider":"Google","rawName":"Gemini-2.5-Pro-06-05","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":74.2,"unit":"%","rank":2,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"o3","modelName":"o3","provider":"OpenAI","rawName":"O3 (High)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":72,"unit":"%","rank":3,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-r1-may-2025","modelName":"DeepSeek-R1 (May 2025)","provider":"DeepSeek","rawName":"DeepSeek-R1-0528","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":70.5,"unit":"%","rank":4,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-2-5-pro-may-2025","modelName":"Gemini 2.5 Pro (May 2025)","provider":"Google","rawName":"Gemini-2.5-Pro-05-06","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":68.1,"unit":"%","rank":5,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"openreasoning-nemotron-32b","modelName":"OpenReasoning-Nemotron-32B","provider":"NVIDIA","rawName":"OpenReasoning-Nemotron-32B","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":66.6,"unit":"%","rank":6,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"exaone-4-0-32b","modelName":"EXAONE-4.0-32B","provider":null,"rawName":"EXAONE-4.0-32B","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":66.6,"unit":"%","rank":6,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"grok-3-mini","modelName":"Grok-3 mini","provider":"xAI","rawName":"Grok-3-Mini (High)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":62.6,"unit":"%","rank":8,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"opencodereasoning-nemotron-1-1-32b","modelName":"OpenCodeReasoning-Nemotron-1.1-32B","provider":"NVIDIA","rawName":"OpenCodeReasoning-Nemotron-1.1-32B","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":62.4,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"xbai-o4","modelName":"XBai-o4-medium","provider":null,"rawName":"XBai-o4-medium","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":60.4,"unit":"%","rank":10,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-2-5-flash-may-2025","modelName":"Gemini 2.5 Flash (May 2025)","provider":"Google","rawName":"Gemini-2.5-Flash-05-20","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":59.3,"unit":"%","rank":11,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"qwen3-235b-a22b","modelName":"Qwen3-235B-A22B","provider":"Alibaba (Qwen)","rawName":"Qwen3-235B-A22B","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":59.3,"unit":"%","rank":11,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gemini-2-5-flash-apr-2025","modelName":"Gemini 2.5 Flash (Apr 2025)","provider":"Google","rawName":"Gemini-2.5-Flash-04-17","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":56.6,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"o3-mini","modelName":"o3-mini","provider":"OpenAI","rawName":"O3-Mini-2025-01-31 (Low)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":51.1,"unit":"%","rank":14,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-opus-4","modelName":"Claude Opus 4","provider":"Anthropic","rawName":"Claude-Opus-4 (Thinking)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":51.1,"unit":"%","rank":14,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-sonnet-4","modelName":"Claude Sonnet 4","provider":"Anthropic","rawName":"Claude-Sonnet-4 (Thinking)","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":48.9,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-5-sonnet","modelName":"Claude 3.5 Sonnet","provider":"Anthropic","rawName":"Claude-3.5-Sonnet-20241022","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":34.8,"unit":"%","rank":17,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-may-2024","modelName":"GPT-4o (May 2024)","provider":"OpenAI","rawName":"GPT-4O-2024-08-06","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":28.4,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4-turbo-nov-2023","modelName":"GPT-4 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-4-Turbo-2024-04-09","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":27.9,"unit":"%","rank":19,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"gpt-4o-mini","modelName":"GPT-4o mini","provider":"OpenAI","rawName":"GPT-4O-mini-2024-07-18","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":26.7,"unit":"%","rank":20,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"claude-3-haiku","modelName":"Claude 3 Haiku","provider":"Anthropic","rawName":"Claude-3-Haiku","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":23.9,"unit":"%","rank":21,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"},{"model":"deepseek-v3","modelName":"DeepSeek-V3","provider":"DeepSeek","rawName":"DeepSeek-V3","variant":"codegen-2025","setting":"Code generation, 182 problems dated 2025-01-01…2025-04-07","score":14.9,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"official","source":"livecodebench","sourceUrl":"https://livecodebench.github.io/leaderboard.html","collected":"2026-10-10"}]}