Compare / GPT-6 Luna vs gpt-oss-120b
GPT-6 Luna vs gpt-oss-120b
13 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-6 Luna | gpt-oss-120b |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 44.3% | 4.4% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,422 | 1,385 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,452 | 1,351 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,403 | 1,277 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,505 | 1,357 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,443 | 1,323 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,352 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,415 | 1,309 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 38.1 | 11.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 38.5% | 19.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.3% | 52.0% |
| Artificial Analysisreported | SciCode% of problems | 54.6% | 34.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 12.6% | 0.0% |
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.