Compare / Gemini 3.7 Flash vs Grok 4.3
Gemini 3.7 Flash vs Grok 4.3
21 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.7 Flash | Grok 4.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,428 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,483 | 1,440 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,492 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,512 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,487 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.1 | 42.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 24.9 |
| Artificial Analysisreported | GPQA Diamond% of questions | 94.5% | 90.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.9% | 37.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.0% | 75.0% |
| Artificial Analysisreported | SciCode% of problems | 59.8% | 48.3% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 85.8% | 39.7% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 13.6% | 0.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 35.5% | 12.4% |
| GDP.pdfreported | Professional document tasks% of rubric | 23.8% | 8.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 69.2% | 33.2% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 7.0% | 21.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 77.5 | 57.7 |
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.