← Arena leaderboards

Confirmed Success

Arena · 50 models

RankModelScore
1Claude Opus 5.5 (Max)0.1978
2Claude Sonnet 5.5 (Max)0.1976
3Gemini 4 Carbon (High)0.1783
4GPT-6 Astra (Max)0.1369
5Gemini 4 Argon (High)0.127
6Claude Fable 5.1 (Max)0.1239
7Muse Wonder Full (Max)0.1188
8GPT-6.1 Sol (Max)0.1149
9Claude Opus 5 (Max)0.1142
10GPT-6.1 Terra (Max)0.0972
11Muse Wonder (Max)0.0679
12MiMo-V2.6-Flash0.0554
13Claude Fable 5 (High)0.0518
14MiMo-V2.6-Pro0.0513
15Grok 4.7 (xHigh)0.0508
16Hy4 preview0.0439
17Qwen3.8-Max0.0405
18DeepSeek-V4.1-Flash-20261017 (Max)0.0385
19GPT-6 Sol (Max)0.0385
20Muse Spark 1.3 (Max)0.0382
21Kimi K3 (Max)0.0377
22Kimi K3.1 Pro (Max)0.0365
23GLM-5.3 (Max)0.0362
24GLM-5.2 (Max)0.0279
25GLM-5.3-Flash0.0238
26Claude Haiku 5.5 (High)0.019
27MiniMax-M3.1-Flash0.0177
28GPT-5.6 Sol (xHigh)0.0173
29Gemini 3.8 Flash (High)0.0123
30Qwen3.8-Flash-Next0.0099
31Claude Sonnet 5 (High)0.0024
32Step 5 Preview-0.0036
33GPT-6 Luna (Max)-0.004
34Mistral Large 4-0.0114
35Grok 4.6 (xHigh)-0.0157
36Qwen3.8-27B-0.0255
37DeepSeek-V4-Pro (High, 20260813)-0.0281
38Gemini 3.7 Flash (High)-0.0303
39Muse Spark 1.1-0.0659
40GPT-6 Luna (Medium)-0.0667
41GPT-5.6 Terra (xHigh)-0.0706
42Spark-X2.6-0.0788
43Qwen3.7-Plus-0.0889
44Muse Spark 1.2 (xHigh)-0.0929
45Qwen3.7-Max-0.1017
46Beam 1.0 501B A23B-0.1044
47MiMo-V2.5-Pro-0.1084
48Hy3-0.1143
49Gemini 3.1 Pro Preview-0.1184
50GPT-6 Luna (Low)-0.1573