Compare / Claude Sonnet 4.6 vs GPT-5.6 Luna
Claude Sonnet 4.6 vs GPT-5.6 Luna
23 results from 6 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 4.6 | GPT-5.6 Luna |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,478 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,461 | 1,461 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,449 | 1,412 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,506 | 1,491 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,446 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,454 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,455 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 63.0 | 71.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 30.1 | 37.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 87.5% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 33.6% | 39.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 50.1% | 53.6% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 71.2% | 80.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 3.0% | 11.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.4% | 31.1% |
| GDP.pdfreported | Professional document tasks% of rubric | 18.0% | 22.7% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 35.5% | 41.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 2.0% | 15.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 64.5 | 53.7 |
| Vending-Bench 2reported | Money after a yearUS dollars | $7,204.14 | $4,094.71 |
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.