Compare / Qwen2.5 72B Instruct vs Claude Haiku 4.5
Qwen2.5 72B Instruct vs Claude Haiku 4.5
9 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen2.5 72B Instruct | Claude Haiku 4.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,299 | 1,420 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,254 | 1,387 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,295 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,292 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,303 | 1,414 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,282 | 1,399 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 21.0% | 6.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.39 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 31.5 | 52.2 |
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.