Compare / Qwen3.8 Max (0902) vs Gemma 4 31B
Qwen3.8 Max (0902) vs Gemma 4 31B
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.8 Max (0902) | Gemma 4 31B |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,471 | 1,450 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,480 | 1,449 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,419 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,510 | 1,499 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,472 | 1,453 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,453 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.2 | 43.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 45.4 | 14.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.8% | 85.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 43.1% | 23.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.3% | 69.7% |
| Artificial Analysisreported | SciCode% of problems | 52.1% | 45.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 88.8% | 43.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 38.9% | 0.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 47.8% | 14.8% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 47.3% | 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.