Compare / Qwen3 235B A22B Thinking 2507 vs Qwen3.7 Max
Qwen3 235B A22B Thinking 2507 vs Qwen3.7 Max
13 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3 235B A22B Thinking 2507 | Qwen3.7 Max |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 22.1 | 66.0 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 12.7 | 29.5 |
| Artificial Analysisreported | GPQA Diamond% of questions | 79.0% | 92.3% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 15.9% | 40.5% |
| Artificial Analysisreported | IFBench% of instructions | 51.2% | 80.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 72.0% | 79.0% |
| Artificial Analysisreported | SciCode% of problems | 41.4% | 49.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 12.0% | 74.5% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 1.5% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 13.6% | 50.8% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 7.8% | 11.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 53.2% | 94.7% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 40.4% | 55.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.