Compare / Claude Opus 4.5 vs Claude Opus 5

Claude Opus 4.5 vs Claude Opus 5

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

Claude Opus 4.5
Anthropic · profile
Claude Opus 5
Anthropic · profile
Results compared
10
Shared sources
2
BenchmarkMetricClaude Opus 4.5Claude Opus 5
Arena (formerly LMArena)reportedOverallArena rating 1,4651,490
Arena (formerly LMArena)reportedOverallArena rating 1,4591,488
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4721,486
Arena (formerly LMArena)reportedCreative writingArena rating 1,4691,472
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5031,543
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4831,497
Arena (formerly LMArena)reportedOverallArena rating 1,4741,491
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4671,482
tau2-benchreportedConsistency (pass^4)% of tasks 11.3%32.0%
tau2-benchreportedTask success (pass^1)% of tasks 24.7%48.7%

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.