Compare / Claude Fable 5.1 vs GLM 5

Claude Fable 5.1 vs GLM 5

15 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Claude Fable 5.1
Anthropic · profile
GLM 5
Z.ai · profile
Results compared
15
Shared sources
4
BenchmarkMetricClaude Fable 5.1GLM 5
Arena (formerly LMArena)reportedOverallArena rating 1,5011,452
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4851,451
Arena (formerly LMArena)reportedCreative writingArena rating 1,4841,447
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5161,481
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4971,446
Arena (formerly LMArena)reportedOverallArena rating 1,5011,457
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4961,447
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 53.427.9
Artificial AnalysisreportedGPQA Diamond% of questions 93.7%82.0%
Artificial AnalysisreportedHumanity's Last Exam% of questions 59.1%29.3%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 85.3%75.7%
UGI LeaderboardreportedRequested-length error% off the requested word count 3.0%34.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.430.40
UGI LeaderboardreportedWriting scorescore out of 100 63.955.0
Vending-Bench 2reportedMoney after a yearUS dollars $5,421.56$4,432.12

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.