The Model Index
Up to four models

GLM-5.3-Flash vs Claude Sonnet 4.6

On the index (GPT-4 = 100), GLM-5.3-Flash scores 161 and Claude Sonnet 4.6 159. 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 GLM-5.3-Flash
Presets
GLM-5.3-Flash
161145–177
WeightsOpen
ReleasedAug 2026
Price in / out$0.15 / $0.50
Context1.05M
Core tests taken6 of 9
Claude Sonnet 4.6
159143–175
WeightsClosed
ReleasedFeb 2026
Price in / out$3.0 / $15
Context1M
Core tests taken5 of 9

GLM-5.3-Flash and Claude Sonnet 4.6 are too close to call (2 points apart, within the uncertainty), ahead on 4 of 4 shared core tests, and costs 25× less.

Test by testthird-party results

GLM-5.3-FlashClaude Sonnet 4.6
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 ProMMMU ProMMMU ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGLM-5.3-FlashClaude Sonnet 4.6
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.1%87.4%
LiveBench Data Analysis76.4%78.0%
LiveBench IF52.8%63.2%
LiveBench Language77.3%76.1%
LiveBench Reasoning77.6%84.8%
GPQA Diamond (Vals AI)86.4%85.6%
MMLU Pro86.1%87.3%
MMMU Pro86.0%83.6%
Maths
AIME-style maths (OTIS mock)93.9%85.8%
LiveBench Mathematics81.2%87.0%
Chess puzzles21.0%23.0%
Coding
LiveBench Agentic Coding56.8%42.6%
LiveBench Coding79.0%79.3%
Code Migration20.5%39.9%
LiveCodeBench80.5%82.1%
ProgramBench0.0%0.5%
SWE-bench92.0%77.4%
Vibe Code Bench v1.130.8%51.5%
DeepSWE63.4%29.9%
Agents
APEX-Agents52.8%43.0%
SkillsBench40.2%49.0%
Mystery game puzzles8.0%16.0%
Professional work
Finance Agent (v2)57.9%51.0%
EMB55.9%60.2%
LegalBench83.9%82.1%
Legal Research Bench45.2%38.5%
Tax Agent Bench31.6%25.8%
TaxEval v275.6%77.1%
Novel problems
ARC-AGI-265.8%60.4%
ARC-AGI-191.0%86.5%

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

This page as a chartDownload PNG