Meta Llama 3 70B Instruct — Benchmarks
Benchmark scores for Meta Llama 3 70B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #97 of 123 open modelscomposite 32/100 across 5 benchmarks in 3 categories · methodology
Knowledge
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 4.3% | #60 / 74 | #243 / 270 |
| MATH Level 5 | 22.6% | #25 / 32 | #88 / 108 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 40.6% | #60 / 83 | #245 / 291 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.