DeepSeek
DeepSeek LLM 67B benchmark results
5 results on 5 benchmarks from 3 sources.
Open weights Released: Nov 29, 2023 Updated Oct 22, 2026
Also listed as: deepseek-llm-67b-chat · deepseek-ai/deepseek-llm-67b-chat
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1185 | 351 | Overall, style control on; 4932 votes; 95% CI 1173–1196“deepseek-llm-67b-chat” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 27.3% | 1360 | Average of 6 normalised benchmarks; bfloat16; 67B params“deepseek-ai/deepseek-llm-67b-chat” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 24.6% | 274 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 0.8% | 258 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 28, 2026 |
| MATH Level 5 | 6.4% | 100 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these DeepSeek LLM 67B scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.