Qwen3 8B — Benchmarks
Benchmark scores for Qwen3 8B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #95 of 123 open modelscomposite 33.3/100 across 4 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 22.6% | #45 / 50 | #150 / 155 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 56.1% | #36 / 74 | #159 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 56.8% | #40 / 83 | #197 / 291 |
| CritPt | 0.0% | #48 / 50 | #164 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.