Deepseek Llm 67B Chat — Benchmarks
Benchmark scores for Deepseek Llm 67B Chat aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Math
| Benchmark | Score | Rank |
|---|---|---|
| MATH Level 5 | 6.4% | #20 / 23 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 24.6% | #27 / 28 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.