⌕Is ___ SOTA?
benchmarks / lmarena-webdev

LMArena WebDev

Arena score. Status active. Contamination risk low. Maintainer LMArena. Source.

ModelScoreDateKind
Claude Sonnet 4.5 20250929 Thinking1390.43757631561242026-01-24snapshot
Claude Opus 4.11388.83190278211352026-02-01snapshot
Claude Sonnet 4.513862026-01-29snapshot
GLM 4.61366.7359368931932025-12-23snapshot
Minimax M21305.5132136654732025-11-25snapshot
Claude Haiku 4.51276.0408707804442025-11-17snapshot
Gemini 2.5 Pro1177.68627911378422025-11-12snapshot
Grok Code Fast 11123.90019700508152025-11-12snapshot
Gemini 3 Pro1438.34042240681632026-04-17snapshot
GPT-51393.5869400815522026-02-06snapshot
GPT-5.11357.8507413276612025-12-11snapshot
Kimi K2 Thinking Turbo1345.32045069669632025-12-11snapshot
Qwen3 Coder 480B A35b Instruct1289.18371325232832025-11-21snapshot
DeepSeek V3.2 Exp1293.0721938428312025-11-25snapshot
GPT-5.11388.5666082763772026-02-01snapshot
GPT-5.1 Codex1341.25506934186962025-12-04snapshot
Claude Opus 4.5 20251101 Thinking1490.40559618926952026-05-25snapshot
Claude Opus 4.51467.20875798173852026-05-04snapshot
GPT-5.21396.8429177685752026-02-06snapshot
Gemini 3 Flash1435.47734758749682026-04-02snapshot
DeepSeek V3.2 Thinking1368.8534773051152025-12-22snapshot
GLM 4.71440.00480541342042026-04-21snapshot
Minimax M2 1 Preview1406.61106758370832026-02-12snapshot
Kimi K2 5 Thinking1433.11120550738952026-03-16snapshot
Claude Opus 4.61536.81195629229392026-07-24snapshot
Kimi K2 5 Instant1421.56106236044522026-02-17snapshot
Claude Opus 4.6 Thinking1545.4546364848512026-08-01snapshot
Gemini 3.1 Pro Preview1456.90709315790242026-04-23snapshot
GLM 51439.70511586458222026-04-14snapshot
Minimax M2 51422.4805984141722026-03-04snapshot