Compare / Gemini 3.7 Flash vs GPT-6 Sol
Gemini 3.7 Flash vs GPT-6 Sol
19 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 | GPT-6 Sol |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 67.8% | 54.3% |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.00 | 0.11 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.03 | 0.11 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.00 | 0.15 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,424 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,483 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,492 | 1,451 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,512 | 1,507 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,487 | 1,447 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,457 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,440 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 47.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.9% | 47.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.0% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 59.8% | 57.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 13.6% | 43.9% |
| GDP.pdfreported | Professional document tasks% of rubric | 23.8% | 26.4% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 69.2% | 60.7% |
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.