Compare / Gemini 3.5 Flash vs Gemini 3.5 Flash Lite
Gemini 3.5 Flash vs Gemini 3.5 Flash Lite
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 | Gemini 3.5 Flash Lite |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0289 | $0.0058 |
| BulletBenchmeasured by us | Games lost on time% of games | 25.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.5% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 810 | 780 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.2 s | 0.9 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0213 | $0.0070 |
| BulletBenchmeasured by us | Games lost on time% of games | 33.3% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.6% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 727 | 892 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.2 s | 0.9 s |
| Arena (formerly LMArena)reported | OverallArena rating | 1,476 | 1,448 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,468 | 1,454 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,466 | 1,435 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,491 | 1,467 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,465 | 1,444 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,456 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,442 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 70.1 | 49.3 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 33.6 | 22.2 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.2% | 83.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 42.7% | 18.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 74.3% | 76.0% |
| Artificial Analysisreported | SciCode% of problems | 53.9% | 41.3% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 78.7% | 53.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 6.6% | 1.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 32.2% | 17.5% |
| GDP.pdfreported | Professional document tasks% of rubric | 14.0% | 10.0% |
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.