Compare / GPT-6 Luna vs Grok 4.3
GPT-6 Luna vs Grok 4.3
14 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-6 Luna | Grok 4.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,422 | 1,428 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,452 | 1,440 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,403 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,505 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,443 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,415 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 38.1 | 24.9 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 38.5% | 37.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.3% | 75.0% |
| Artificial Analysisreported | SciCode% of problems | 54.6% | 48.3% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 12.6% | 0.0% |
| GDP.pdfreported | Professional document tasks% of rubric | 23.0% | 8.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 41.4% | 33.2% |
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.