Compare / Qwen3 235B A22B Thinking 2507 vs o4 Mini

Qwen3 235B A22B Thinking 2507 vs o4 Mini

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

Qwen3 235B A22B Thinking 2507
Alibaba · profile
o4 Mini
OpenAI · profile
Results compared
10
Shared sources
3
BenchmarkMetricQwen3 235B A22B Thinking 2507o4 Mini
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4041,379
Arena (formerly LMArena)reportedCreative writingArena rating 1,3701,337
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4661,408
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3851,369
Arena (formerly LMArena)reportedOverallArena rating 1,4001,391
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3771,354
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 40.4%19.6%
UGI LeaderboardreportedRequested-length error% off the requested word count 30.0%19.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.310.33
UGI LeaderboardreportedWriting scorescore out of 100 32.446.9

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.