Llama 7B — Benchmarks
Benchmark scores for Llama 7B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Knowledge
Math
| Benchmark | Score | Rank |
|---|---|---|
| GSM8K | 11.0% | #24 / 27 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| BIG-Bench Hard | 30.3% | #10 / 11 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.