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 GPT-6 Astra Cheapest at this level GPT-6.1 Sol Best open model, measured Hy4 preview 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
GPT-6 Astra 199 183–216
Weights Closed
Released Sep 2026
Price in / out $10 / $50
Context 1.05M
Core tests taken 7 of 9
Claude Opus 5.5 199 182–215
Weights Closed
Released Sep 2026
Price in / out $4.0 / $20
Context 1M
Core tests taken 6 of 9
GPT-6 Astra and Claude Opus 5.5 are too close to call (1 points apart, within the uncertainty), ahead on 3 of 6 shared core tests, at 2.5× 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 EBR-benchEBR-bench 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 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 1-100Vibe Code Bench 1-100 Vibe Code Bench v1.1Vibe Code Bench v1.1 FrontierSWEFrontierSWE AGENTS APEX-AgentsAPEX-Agents BioMysteryBenchBioMysteryBench SRE BenchSRE Bench Terminal-Bench ScienceTerminal-Bench Science DTBenchDTBench Furniture assemblyFurniture assembly 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 SAGESAGE Tax Agent BenchTax Agent Bench NOVEL PROBLEMS ARC-AGI-2ARC-AGI-2 ARC-AGI-1ARC-AGI-1 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.