Compare / Gemini 3.5 Flash vs GPT-6 Luna
Gemini 3.5 Flash vs GPT-6 Luna
20 results from 6 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 | GPT-6 Luna |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0289 | $0.0016 |
| BulletBenchmeasured by us | Games lost on time% of games | 25.0% | 50.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.5% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 810 | 249 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.2 s | 1.5 s |
| APEX-Agentsreported | Tasks passed% of tasks | 27.5% | 44.3% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,476 | 1,422 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,468 | 1,452 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,466 | 1,403 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,491 | 1,505 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,465 | 1,443 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,415 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 33.6 | 38.1 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 42.7% | 38.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 74.3% | 83.3% |
| Artificial Analysisreported | SciCode% of problems | 53.9% | 54.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 6.6% | 12.6% |
| GDP.pdfreported | Professional document tasks% of rubric | 14.0% | 23.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 66.2% | 41.4% |
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.