Compare / Claude Opus 5.5 vs gpt-oss-120b
Claude Opus 5.5 vs gpt-oss-120b
15 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 5.5 | gpt-oss-120b |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 73.5% | 4.4% |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,499 | 1,351 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,521 | 1,277 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,556 | 1,357 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,516 | 1,323 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,509 | 1,352 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,520 | 1,309 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 57.6 | 11.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 61.4% | 19.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.7% | 52.0% |
| Artificial Analysisreported | SciCode% of problems | 66.9% | 34.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 59.6% | 0.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 2.0% | 107.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.43 | 0.29 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 70.0 | 38.5 |
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.