The Model Index
Up to four models

Claude Fable 5 vs GLM-5.2

On the index (GPT-4 = 100), Claude Fable 5 scores 183 and GLM-5.2 154. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Fable 5
Presets
Claude Fable 5
183167–199
WeightsClosed
ReleasedJun 2026
Price in / out$10 / $50
Context1M
Core tests taken6 of 9
GLM-5.2
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9

Claude Fable 5 leads GLM-5.2 by 30 points, ahead on 5 of 5 shared core tests, at 12× the price.

Test by testthird-party results

Claude Fable 5GLM-5.2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)LiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProEBR-benchEBR-benchSimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)Surface Evolver BenchSurface Evolver BenchCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEMirrorCodeMirrorCodeWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestClaude Fable 5GLM-5.2
Reasoning & knowledge
GPQA Diamond (Epoch AI)93.9%91.9%
LiveBench Data Analysis80.5%73.7%
LiveBench IF75.8%62.3%
LiveBench Language90.7%76.2%
LiveBench Reasoning89.6%78.6%
GPQA Diamond (Vals AI)93.2%85.6%
MMLU Pro91.5%86.7%
EBR-bench39.5%9.5%
SimpleBench81.9%58.8%
SimpleQA Verified70.7%34.2%
Maths
FrontierMath (tiers 1-3)87.0%59.2%
AIME-style maths (OTIS mock)100.0%86.4%
LiveBench Mathematics96.0%89.8%
Chess puzzles47.0%22.0%
FrontierMath (tier 4)90.2%29.3%
Surface Evolver Bench95.0%55.6%
Coding
LiveBench Agentic Coding62.2%51.8%
LiveBench Coding86.0%79.7%
Code Migration55.1%37.9%
LiveCodeBench89.8%69.5%
ProgramBench2.0%0.5%
SWE-bench95.0%82.8%
Vibe Code Bench v1.190.3%64.0%
DeepSWE69.9%43.8%
MirrorCode70.0%36.7%
WeirdML91.9%70.1%
Agents
APEX-Agents63.6%45.2%
DTBench98.4%93.6%
LMCA61.2%45.8%
Mystery game puzzles52.0%19.0%
Professional work
Finance Agent (v2)56.3%49.7%
CorpFin v271.8%66.1%
EMB73.7%61.5%
LegalBench88.6%84.1%
Legal Research Bench49.5%31.3%
MedCode56.1%40.8%
MedScribe88.5%83.5%
TaxEval v276.9%73.3%
Novel problems
ARC-AGI-289.2%22.8%
ARC-AGI-198.5%77.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG