Compare / Qwen3.5-Flash vs gpt-oss-120b
Qwen3.5-Flash vs gpt-oss-120b
10 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.5-Flash | gpt-oss-120b |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,414 | 1,385 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,403 | 1,351 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,338 | 1,277 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,420 | 1,357 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,381 | 1,323 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,396 | 1,352 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,367 | 1,309 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.8% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 10.5% | 14.2% |
| Vending-Bench 2reported | Money after a yearUS dollars | $462.69 | $-21.53 |
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.