Compare / olmo-3-32b-think vs GPT-5.2
olmo-3-32b-think vs GPT-5.2
10 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | olmo-3-32b-think | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,319 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,308 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,265 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,303 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,298 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,306 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,275 | 1,411 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 102.0% | 76.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.32 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 28.5 | 49.4 |
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.