Qwen3.6 27B — Benchmarks
Benchmark scores for Qwen3.6 27B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #16 of 78 open modelscomposite 56/100 across 11 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LiveBench Coding | 71.8 | #13 / 19 | #52 / 63 |
| SciCode | 37.3% | #32 / 62 | #126 / 161 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| FrontierMath | 35.1% | #12 / 15 | #54 / 102 |
| LiveBench Math | 79.9 | #16 / 19 | #56 / 63 |
| AIME 2024/2025 | 91.1% | #10 / 82 | #58 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Chess Puzzles | 22.0% | #6 / 65 | #74 / 205 |
| Mystery Game Puzzles | 7.0% | #15 / 17 | #111 / 122 |
| DTBench | 78.1% | #26 / 67 | #119 / 210 |
| LMCA | 34.5% | #15 / 53 | #104 / 172 |
| GPQA Diamond | 85.9% | #17 / 94 | #75 / 289 |
| CritPt | 0.9% | #34 / 62 | #119 / 172 |
| LiveBench Reasoning | 70.3 | #19 / 19 | #62 / 63 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.