Qwen3 14B — Benchmarks
Benchmark scores for Qwen3 14B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #76 of 123 open modelscomposite 41.3/100 across 4 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 31.6% | #40 / 50 | #137 / 155 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 66.4% | #29 / 74 | #138 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 63.8% | #36 / 83 | #185 / 291 |
| CritPt | 0.0% | #46 / 50 | #162 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.