Compare / o4 Mini vs GLM 5.2

o4 Mini vs GLM 5.2

11 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

o4 Mini
OpenAI · profile
GLM 5.2
Z.ai · profile
Results compared
11
Shared sources
3
BenchmarkMetrico4 MiniGLM 5.2
Arena (formerly LMArena)reportedOverallArena rating 1,3681,463
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3791,463
Arena (formerly LMArena)reportedCreative writingArena rating 1,3371,455
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4081,500
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3691,470
Arena (formerly LMArena)reportedOverallArena rating 1,3911,476
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3541,459
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 19.6%34.2%
UGI LeaderboardreportedRequested-length error% off the requested word count 19.0%12.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.330.37
UGI LeaderboardreportedWriting scorescore out of 100 46.967.0

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.