Compare / Qwen3.7 Max vs Gemma 4 31B
Qwen3.7 Max vs Gemma 4 31B
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 | Qwen3.7 Max | Gemma 4 31B |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 66.0 | 43.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 29.5 | 14.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.3% | 85.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 40.5% | 23.6% |
| Artificial Analysisreported | IFBench% of instructions | 80.5% | 75.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.0% | 69.7% |
| Artificial Analysisreported | SciCode% of problems | 49.5% | 45.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 74.5% | 43.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 1.5% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 50.8% | 36.4% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 11.8% | 14.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 94.7% | 65.5% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 55.8% | 10.4% |
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.