Qwen3.5 9B — Benchmarks
Benchmark scores for Qwen3.5 9B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #35 of 78 open modelscomposite 48/100 across 9 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 27.6% | #51 / 62 | #147 / 161 |
| Terminal-Bench | 9.2% | #15 / 16 | #56 / 57 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 82.5% | #17 / 144 | #53 / 257 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 61.7% | #35 / 82 | #151 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Chess Puzzles | 12.0% | #23 / 65 | #128 / 205 |
| DTBench | 71.2% | #31 / 67 | #133 / 210 |
| LMCA | 24.5% | #28 / 53 | #128 / 172 |
| GPQA Diamond | 79.0% | #24 / 94 | #116 / 289 |
| CritPt | 0.3% | #41 / 62 | #133 / 172 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.