Llama 3.1 8B Instruct — Benchmarks
Benchmark scores for Llama 3.1 8B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #98 of 123 open modelscomposite 31.2/100 across 10 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 13.2% | #49 / 50 | #154 / 155 |
Knowledge
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 1.7% | #67 / 74 | #258 / 270 |
| MATH Level 5 | 22.9% | #23 / 32 | #86 / 108 |
| GSM8K | 82.4% | #12 / 60 | #19 / 93 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 27.0% | #74 / 83 | #278 / 291 |
| CritPt | 0.0% | #41 / 50 | #149 / 167 |
| PIQA | 81.2% | #15 / 35 | #30 / 60 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.