Compare / Gemini 3.5 Flash vs gemini-3-pro
Gemini 3.5 Flash vs gemini-3-pro
21 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.5 Flash | gemini-3-pro |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,461 | 1,451 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,476 | 1,481 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,468 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,466 | 1,484 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,491 | 1,498 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,465 | 1,473 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,485 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,481 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 33.6 | 28.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.2% | 90.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 42.7% | 39.7% |
| Artificial Analysisreported | IFBench% of instructions | 76.3% | 70.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 74.3% | 76.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 46.2% | 41.7% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 95.6% | 87.1% |
| OpenHands Indexreported | Average% resolved | 62.6% | 49.0% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 39.7% | 36.8% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 37.5% | 25.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 81.2% | 44.2% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 78.6% | 70.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 76.2% | 68.6% |
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.