WebDev

Arena · 50 models

Rank	Model	Score
1	Claude Opus 5.5 (Max)	1,809.8392
2	GPT-6 Astra (Max)	1,773.3546
3	Claude Sonnet 5.5 (xHigh)	1,769.7284
4	Gemini 4 Carbon (High)	1,768.1522
5	GPT-6.1 Sol (Max)	1,750.5682
6	Claude Fable 5.1 (Max)	1,745.8518
7	Muse Wonder Full (Max)	1,725.3158
8	Claude Sonnet 5.5 (High)	1,710.5864
9	Kimi K3.1 Pro (Max)	1,694.5824
10	Claude Opus 5 (Max)	1,690.5239
11	Gemini 4 Argon (High)	1,679.2118
12	GPT-6 Sol (Max)	1,678.1896
13	Qwen3.8-Max (0902)	1,675.9356
14	GPT-6.1 Terra (Max)	1,672.6547
15	Qwen3.8-Max	1,671.8853
16	DeepSeek-V4.1-Flash-20261017 (Max)	1,665.0404
17	Claude Opus 5 (High)	1,658.1898
18	Kimi K3 (Max)	1,656.3909
19	Muse Spark 1.3 (Max)	1,656.2349
20	Muse Wonder (Max)	1,652.094
21	Grok 4.7 (xHigh)	1,637.4572
22	MiMo-V2.6-Flash	1,637.1737
23	Hy4 preview	1,631.1069
24	Qwen3.8-Flash-Next	1,628.3221
25	MiMo-V2.6-Pro	1,625.4175
26	Claude Fable 5 (High)	1,624.0826
27	GLM-5.3 (Max)	1,622.8099
28	Muse Spark 1.3 (xHigh)	1,620.0644
29	DeepSeek-V4.1-Flash-20260910 (Max)	1,619.1588
30	Grok 4.6 (High)	1,616.3867
31	GPT-5.6 Sol (xHigh, Codex Harness)	1,615.785
32	GLM-5.3-Flash	1,606.6487
33	GLM-5.2 (Max)	1,605.6392
34	Qwen3.8-27B	1,589.7823
35	Gemini 3.7 Flash (High)	1,589.6729
36	Claude Haiku 5.5 (High)	1,588.8331
37	Gemini 3.8 Flash (High)	1,583.2994
38	MiniMax-M3.1-Flash	1,582.4578
39	DeepSeek-V4-Pro (High, 20260813)	1,581.8581
40	DeepSeek-V4-Flash (High)	1,581.838
41	GPT-6 Luna (Max)	1,579.4042
42	Step 5 Preview (High)	1,571.0387
43	Claude Opus 4.7 (High)	1,557.5378
44	Claude Opus 4.8 (High)	1,555.8264
45	Claude Opus 4.7	1,555.4286
46	Grok 4.5	1,553.0325
47	Claude Opus 4.6 (High)	1,546.2356
48	Mistral Large 4	1,544.3103
49	Muse Spark 1.1	1,542.4822
50	Claude Sonnet 5 (High)	1,540.09