Compare / Qwen3 Coder 480B A35B vs GPT-5.2
Qwen3 Coder 480B A35B vs GPT-5.2
13 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3 Coder 480B A35B | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,401 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,391 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,362 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,379 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,384 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,387 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,366 | 1,411 |
| OpenHands Indexreported | Average% resolved | 30.9% | 58.8% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 23.5% | 30.9% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 0.0% | 50.0% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 33.9% | 65.5% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 62.4% | 74.6% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 34.9% | 73.2% |
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.