Qwen 14B Chat — Benchmarks
Benchmark scores for Qwen 14B Chat aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #22 of 73 open modelscomposite 56.5/100 across 3 benchmarks in 3 categories · methodology
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU | 65.0% | #35 / 76 | #79 / 136 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GSM8K | 61.2% | #24 / 59 | #33 / 93 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| BIG-Bench Hard | 55.0% | #15 / 37 | #22 / 50 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.