Compare / gemini-3-flash vs Grok 4.5
gemini-3-flash vs Grok 4.5
14 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-flash | Grok 4.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,439 | 1,464 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,191 | 1,202 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,468 | 1,465 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,469 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,457 | 1,452 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,496 | 1,488 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,458 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,473 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,461 | 1,459 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 26.3 | 38.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.8% | 93.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 36.6% | 42.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 78.0% | 79.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 20.8% | 42.1% |
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.