Compare / Claude Sonnet 5 vs GPT-5.6 Luna
Claude Sonnet 5 vs GPT-5.6 Luna
26 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.01 | -0.05 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | 0.09 | -0.04 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.07 | 0.02 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,476 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,452 | 1,461 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,465 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,435 | 1,412 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,512 | 1,491 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,467 | 1,446 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,462 | 1,454 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,452 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 71.5 | 71.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 38.2 | 37.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 91.1% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 41.3% | 39.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 82.0% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 54.3% | 53.6% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 80.5% | 80.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 14.1% | 11.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 37.3% | 31.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 33.7% | 41.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 3.0% | 15.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.38 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 62.7 | 53.7 |
| Vending-Bench 2reported | Money after a yearUS dollars | $6,377.70 | $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.