Compare / Claude Opus 5.5 vs Gemma 4 31B
Claude Opus 5.5 vs Gemma 4 31B
15 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 5.5 | Gemma 4 31B |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,499 | 1,449 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,521 | 1,419 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,556 | 1,499 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,516 | 1,453 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,509 | 1,453 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,520 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 57.6 | 14.7 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 61.4% | 23.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.7% | 69.7% |
| Artificial Analysisreported | SciCode% of problems | 66.9% | 45.5% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 59.6% | 0.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 72.2% | 10.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 2.0% | 5.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.43 | 0.36 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 70.0 | 43.1 |
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.