Compare / Claude Opus 4.7 vs o3 Mini

Claude Opus 4.7 vs o3 Mini

7 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Claude Opus 4.7
Anthropic · profile
o3 Mini
OpenAI · profile
Results compared
7
Shared sources
2
BenchmarkMetricClaude Opus 4.7o3 Mini
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,5081,328
Arena (formerly LMArena)reportedCreative writingArena rating 1,4881,301
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5351,366
Arena (formerly LMArena)reportedInstruction followingArena rating 1,5031,344
Arena (formerly LMArena)reportedOverallArena rating 1,5021,348
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4961,325
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 51.7%15.3%

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.