Compare / o4 Mini vs GLM 5
o4 Mini vs GLM 5
12 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | o4 Mini | GLM 5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,368 | 1,452 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,379 | 1,451 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,337 | 1,447 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,408 | 1,481 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,369 | 1,446 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,391 | 1,457 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,354 | 1,447 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 19.0% | 34.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 46.9 | 55.0 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 98.7% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 18.6% | 10.1% |
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.