Compare / Qwen3.8 Max (0902) vs GPT-5.2
Qwen3.8 Max (0902) vs GPT-5.2
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 | Qwen3.8 Max (0902) | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,471 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,480 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,510 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,472 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,411 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 45.4 | 30.4 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.8% | 90.3% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 43.1% | 37.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.3% | 82.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 47.8% | 11.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 47.3% | 37.1% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 35.1% | 18.6% |
| tau2-benchreported | Task success (pass^1)% of tasks | 55.2% | 32.2% |
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.