Compare / Gemini 3.6 Flash vs GPT-6 Luna
Gemini 3.6 Flash vs GPT-6 Luna
24 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 3.6 Flash | GPT-6 Luna |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0113 | $0.0016 |
| BulletBenchmeasured by us | Games lost on time% of games | 41.7% | 50.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.3% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 628 | 249 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.6 s | 1.5 s |
| APEX-Agentsreported | Tasks passed% of tasks | 46.9% | 44.3% |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.08 | 0.05 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.09 | -0.03 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.04 | 0.02 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,470 | 1,422 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,472 | 1,452 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,469 | 1,403 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,500 | 1,505 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,473 | 1,443 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,482 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,415 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 34.0 | 38.1 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 40.8% | 38.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 83.3% |
| Artificial Analysisreported | SciCode% of problems | 53.4% | 54.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 7.1% | 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.