Up to four models
Compare Side by side on the same independent tests, with price and context. The link in your address bar shares this exact comparison.
Next to GLM-5.3 Best closed model, measured GPT-6 Astra Closest rival, another lab Kimi K3 Stronger for the same price Gemini 3.8 Flash The version it replaced GLM-5.2 Where it started GPT-4 Presets Best open vs best closed (measured) Today vs GPT-4 (2023) Top three labs US vs China, best of each
GLM-5.3 171 155–188
Weights Open
Released Aug 2026
Price in / out $1.4 / $4.4
Context 1.05M
Core tests taken 5 of 9
GPT-6 Luna 169 152–185
Weights Closed
Released Sep 2026
Price in / out $0.10 / $0.50
Context 1.05M
Core tests taken 6 of 9
GLM-5.3 and GPT-6 Luna are too close to call (3 points apart, within the uncertainty), ahead on 4 of 5 shared core tests, at 11× the price.
Test by testindependent results 0% 25% 50% 75% 100% REASONING & KNOWLEDGE GPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI) LiveBench Data AnalysisLiveBench Data Analysis LiveBench IFLiveBench IF LiveBench LanguageLiveBench Language LiveBench ReasoningLiveBench Reasoning SimpleQA VerifiedSimpleQA Verified MATHS FrontierMath (tiers 1-3)FrontierMath (tiers 1-3) AIME-style maths (OTIS mock)AIME-style maths (OTIS mock) LiveBench MathematicsLiveBench Mathematics ProofBench v1.1ProofBench v1.1 Chess puzzlesChess puzzles FrontierMath (tier 4)FrontierMath (tier 4) CODING Terminal-Bench 4.0Terminal-Bench 4.0 LiveBench Agentic CodingLiveBench Agentic Coding LiveBench CodingLiveBench Coding Code MigrationCode Migration CyberBench v1.1CyberBench v1.1 IOIIOI ProgramBenchProgramBench Terminal-Bench 2.1Terminal-Bench 2.1 Vibe Code Bench v1.1Vibe Code Bench v1.1 AGENTS APEX-AgentsAPEX-Agents Terminal-Bench ScienceTerminal-Bench Science DTBenchDTBench LMCALMCA Mystery game puzzlesMystery game puzzles PROFESSIONAL WORK Finance Agent (v2)Finance Agent (v2) EMBEMB Harvey's Legal Agent BenchmarkHarvey's Legal Agent Benchmark Legal Research BenchLegal Research Bench MedCodeMedCode MedScribeMedScribe Public Benefits Bench v1.1Public Benefits Bench v1.1 Tax Agent BenchTax Agent Bench NOVEL PROBLEMS MysteryMechanismMysteryMechanism Only tests that at least two of these models have taken. Bold rows are the core tests shown on every profile; all of these results inform the index score. Task length (METR) is listed below the chart because it is a duration, not a percentage.