Llama 2 70B Chat — Benchmarks
Benchmark scores for Llama 2 70B Chat 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 | 59.9% | #21 / 36 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| GSM8K | 58.7% | #14 / 27 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| BIG-Bench Hard | 58.5% | #4 / 11 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.