AClaude Sonnet 4.6
claude-sonnet family · launched 2026-02-17
MultimodalReasoningToolsClaude workhorse for coding agents, careful analysis, and production cost control
What this model supports
Strengths by domain
Every result has a source
Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.
Coding1 results
LiveBench 2.0 · CodingLiveBench66.60 scoreReading 66.6
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceResearch & reasoning1 results
LiveBench 2.0 · ResearchLiveBench86.40 scoreReading 86.4
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceProfessional work1 results
LiveBench 2.0 · ProfessionalLiveBench59.75 scoreReading 59.8
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.
Configuration: LiveBench 2.0Open evidenceKnowledge & instruction1 results
LiveBench 2.0 · KnowledgeLiveBench63.60 scoreReading 63.6
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.
Configuration: LiveBench 2.0Open evidenceHuman preference & indices3 results
LiveBenchLiveBench65.09 scoreReading 65.1
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceAA IndexArtificial Analysis65.49 indexReading 59.8
Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: Claude Sonnet 4.6Open evidenceArena TextLMArena1,457.7 EloReading 59.8
Direct LMArena text leaderboard result.
Open evidence