Compare / Qwen3 Max vs Claude Fable 5.1

Qwen3 Max vs Claude Fable 5.1

15 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Qwen3 Max
Alibaba · profile
Claude Fable 5.1
Anthropic · profile
Results compared
15
Shared sources
5
BenchmarkMetricQwen3 MaxClaude Fable 5.1
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4191,485
Arena (formerly LMArena)reportedCreative writingArena rating 1,3931,484
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4181,516
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4131,497
Arena (formerly LMArena)reportedOverallArena rating 1,4231,501
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4051,496
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 15.653.4
Artificial AnalysisreportedGPQA Diamond% of questions 76.4%93.7%
Artificial AnalysisreportedHumanity's Last Exam% of questions 11.9%59.1%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 50.0%85.3%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 48.7%70.8%
UGI LeaderboardreportedRequested-length error% off the requested word count 23.0%3.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.330.43
UGI LeaderboardreportedWriting scorescore out of 100 38.663.9
Vending-Bench 2reportedMoney after a yearUS dollars $71.56$5,421.56

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.