← Arena leaderboards

Vision · Style Control · Homework

Arena · 50 models

RankModelScore
1GPT-6.1 Sol (Max)1,358.3144
2Claude Fable 5 (High)1,351.8626
3Claude Opus 5.5 (High)1,351.4877
4GPT-6 Astra (Max)1,342.3681
5Gemini 3.8 Flash (High)1,338.4024
6GPT-5.5 (High)1,335.0524
7Claude Fable 5.1 (Max)1,334.3547
8Qwen3.8-Max1,334.2886
9Claude Opus 4.8 (High)1,331.8262
10Claude Opus 4.7 (High)1,330.9046
11GPT-5.51,329.9829
12GPT-5.4 (High)1,329.8132
13Claude Opus 4.71,325.8156
14Claude Sonnet 5.5 (xHigh)1,325.5434
15Claude Opus 4.6 (High)1,324.8731
16Grok 4.7 (xHigh)1,323.6326
17Claude Opus 5 (High)1,323.2579
18GPT-5.6 Terra (xHigh)1,321.0882
19Claude Opus 4.81,320.8187
20Gemini 3.5 Flash (Medium)1,316.2491
21GPT-5.6 Sol (xHigh)1,313.8757
22Claude Opus 4.61,312.2179
23Gemini 3.1 Pro Preview1,310.2359
24Gemini 3.7 Flash (High)1,308.9002
25Gemini 3 Pro1,308.5314
26Gemini 3 Flash1,308.2082
27DeepSeek-V4.1-Flash-20260910 (Max)1,307.4987
28GLM-5.3-Flash1,306.4453
29GPT-6 Sol (Max)1,306.1805
30Gemini 3.5 Flash (High)1,305.7489
31Claude Sonnet 5 (High)1,304.5725
32Gemma 4 31B1,303.8158
33Gemini 3.6 Flash (High)1,303.7486
34GPT-5.41,303.1815
35Kimi K2.61,302.2991
36Claude Sonnet 4.61,302.2958
37Grok 4.51,299.4681
38Muse Spark1,298.5206
39Muse Spark 1.3 (xHigh)1,297.0551
40Grok 4.6 (High)1,296.9951
41Gemini 3 Flash (Minimal)1,296.6975
42Muse Spark 1.3 (Max)1,293.7375
43GPT-5.2 Chat (20260210)1,293.3687
44GPT-5.4 mini (High)1,290.8696
45Gemini 3.5 Flash-Lite1,290.3199
46Kimi K2.5 (Thinking)1,290.0079
47GPT-5.6 Luna (xHigh)1,289.8025
48Qwen3.7-Plus1,288.6792
49Muse Spark 1.11,287.7657
50Qwen3.5-397B-A17B1,287.2396