Compare / Gemini 3.5 Flash Lite vs Gemini 3.6 Flash
Gemini 3.5 Flash Lite vs Gemini 3.6 Flash
27 results from 4 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 Lite | Gemini 3.6 Flash |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0058 | $0.0113 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 41.7% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.3% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 780 | 628 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.9 s | 1.6 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0070 | $0.0050 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 91.7% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 892 | 33 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.9 s | 1.5 s |
| Arena (formerly LMArena)reported | OverallArena rating | 1,448 | 1,470 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,454 | 1,472 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,435 | 1,469 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,467 | 1,500 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,444 | 1,473 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,456 | 1,482 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,442 | 1,472 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 49.3 | 69.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 22.2 | 34.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 83.8% | 92.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 18.8% | 40.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 76.0% | 80.0% |
| Artificial Analysisreported | SciCode% of problems | 41.3% | 53.4% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 53.6% | 77.5% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 1.0% | 7.1% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 17.5% | 29.9% |
| GDP.pdfreported | Professional document tasks% of rubric | 10.0% | 14.0% |
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.