Compare / Qwen3.6 Max Preview vs gpt-oss-120b
Qwen3.6 Max Preview vs gpt-oss-120b
15 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.6 Max Preview | gpt-oss-120b |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,452 | 1,385 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,450 | 1,351 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,436 | 1,277 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,499 | 1,357 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,449 | 1,323 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,460 | 1,352 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,446 | 1,309 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 28.4 | 11.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 88.8% | 78.2% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 30.8% | 19.6% |
| Artificial Analysisreported | IFBench% of instructions | 76.6% | 69.0% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.7% | 52.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 43.9% | 23.5% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 95.9% | 65.8% |
| Vending-Bench 2reported | Money after a yearUS dollars | $4,254.19 | $-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.