Compare / gemini-3-pro vs GPT-5.6 Sol
gemini-3-pro vs GPT-5.6 Sol
16 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | gemini-3-pro | GPT-5.6 Sol |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,451 | 1,489 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,201 | 1,256 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,481 | 1,476 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,474 | 1,485 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,484 | 1,470 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,498 | 1,534 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,473 | 1,489 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,485 | 1,483 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,481 | 1,483 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 28.0 | 47.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 90.8% | 94.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 39.7% | 49.5% |
| Artificial Analysisreported | IFBench% of instructions | 70.4% | 72.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 76.0% | 84.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 41.7% | 65.9% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 87.1% | 85.1% |
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.