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.
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| MMLU | 79.3% | #7 / 36 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 4.3% | #16 / 22 |
| MATH Level 5 | 22.6% | #17 / 23 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 40.6% | #19 / 28 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.