Compare / GPT-5.4 Nano vs GPT-5.6 Luna
GPT-5.4 Nano vs GPT-5.6 Luna
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-5.4 Nano | GPT-5.6 Luna |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,418 | 1,461 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,405 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,335 | 1,412 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,438 | 1,491 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,387 | 1,446 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,401 | 1,454 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,362 | 1,435 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 56.1 | 71.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 20.7 | 37.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 81.7% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 28.3% | 39.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 76.7% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 47.2% | 53.6% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 60.7% | 80.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.5% | 11.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 27.4% | 31.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 11.7% | 41.0% |
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.