Compare / Claude Opus 4.8 vs Gemini 3.7 Flash
Claude Opus 4.8 vs Gemini 3.7 Flash
27 results from 7 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.8 | Gemini 3.7 Flash |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 48.9% | 67.8% |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.04 | 0.00 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | 0.15 | -0.03 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.10 | -0.00 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | -0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,469 | 1,477 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,490 | 1,483 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,492 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,525 | 1,512 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,491 | 1,487 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,480 | 1,488 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,474 | 1,496 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 74.3 | 76.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 41.8 | 39.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.0% | 94.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 48.7% | 47.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.7% | 83.0% |
| Artificial Analysisreported | SciCode% of problems | 54.4% | 59.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 84.6% | 85.8% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 21.7% | 13.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.2% | 35.5% |
| GDP.pdfreported | Professional document tasks% of rubric | 24.0% | 23.8% |
| Remote Labor Indexreported | Projects done to client standard% of projects | 8.3% | 5.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 53.0% | 69.2% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 7.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 65.9 | 77.5 |
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.