LMArena WebDev Arena
People compare two web apps built by anonymous models from the same prompt and vote for the better one.
Claude Opus 5.5
#1 right now
1,818
Arena rating
100
Models ranked
Sep 23, 2026
Board published
Ranking
Best variant per model, as published. Higher is better.
- 11,818
Claude Opus 5.5
as “claude-opus-5.5-max” - 21,792
GPT-6 Astra
as “gpt-6-astra-max” - 31,755
Claude Fable 5.1
as “claude-fable-5.1-max” - 41,692
Claude Opus 5
as “claude-opus-5-max” - 51,686
GPT-6 Sol
as “gpt-6-sol-max” - 61,671
Qwen3.8 Max (0902)
as “qwen3.8-max” - 71,660
Kimi K3
as “kimi-k3-max” - 81,658
Muse Spark 1.3
as “muse-spark-1.3-max” - 91,636
Qwen3.8-Flash-Next
as “qwen3.8-flash-next” - 101,632
Grok 4.7
as “grok-4.7-xhigh” - 111,631
Hy4 preview
as “hy4-preview” - 121,627
Claude Fable 5
as “claude-fable-5-high” - 131,624
Grok 4.6
as “grok-4.6-high” - 141,622
GLM-5.3
as “glm-5.3-max” - 151,620
DeepSeek V4.1 Flash
as “deepseek-v4.1-flash-max” - 161,617
GPT-5.6 Sol
as “gpt-5.6-sol-xhigh (codex-harness)” - 171,612
GLM 5.3 Flash
as “glm-5.3-flash” - 181,600
GLM-5.2
as “glm-5.2-max” - 191,595
Gemini 3.7 Flash
as “gemini-3.7-flash-high” - 201,591
Qwen3.8 27B
as “qwen3.8-27b” - 211,584
Gemini 3.8 Flash
as “gemini-3.8-flash-high” - 221,581
DeepSeek V4 Pro 0813
as “deepseek-v4-pro-high-20260813” - 231,579
DeepSeek V4 Flash Vision
as “deepseek-v4-flash-high” - 241,557
Claude Opus 4.7
as “claude-opus-4-7” - 251,555
Claude Opus 4.8
as “claude-opus-4-8-high”
Rank over time
Rank at each month’s end, from snapshots this board published or we captured.
Other coding boards
Scores as published by LMArena on the capture date (2026-09-24). Source: lmarena.ai leaderboard page data.