Llama 2 13B Chat HF — Benchmarks
Benchmark scores for Llama 2 13B Chat HF aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #38 of 73 open modelscomposite 43.2/100 across 3 benchmarks in 3 categories · methodology
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU | 50.9% | #58 / 76 | #108 / 136 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GSM8K | 36.9% | #37 / 59 | #54 / 93 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| BIG-Bench Hard | 58.2% | #12 / 37 | #19 / 50 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.