Compare / Qwen3.6 Max Preview vs Gemma 4 31B
Qwen3.6 Max Preview vs Gemma 4 31B
15 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.6 Max Preview | Gemma 4 31B |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,452 | 1,450 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,450 | 1,449 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,436 | 1,419 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,499 | 1,499 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,449 | 1,453 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,460 | 1,453 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,446 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 28.4 | 14.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 88.8% | 85.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 30.8% | 23.6% |
| Artificial Analysisreported | IFBench% of instructions | 76.6% | 75.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.7% | 69.7% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 43.9% | 36.4% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 95.9% | 65.5% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 52.0% | 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.