← Arena leaderboards

Text · Style Control · Multi Turn

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,559.4059
2Gemini 4 Argon (High)1,539.0135
3Claude Opus 4.6 (High)1,516.8307
4Muse Wonder (Max)1,516.474
5Claude Fable 5 (High)1,516.1481
6Claude Opus 4.7 (High)1,515.8221
7Claude Opus 4.71,513.815
8Claude Opus 4.61,509.8905
9Muse Spark 1.2 (xHigh)1,507.8225
10Gemini 3.8 Flash (High)1,504.7958
11Kimi K3 (Max)1,502.2465
12Claude Opus 5.5 (High)1,499.3161
13Claude Opus 4.8 (High)1,496.8521
14Gemini 3.1 Pro Preview1,495.9703
15Gemini 3 Pro1,495.7432
16Muse Spark 1.11,495.6497
17Claude Opus 4.81,494.226
18GPT-5.2 Chat (20260210)1,494.1512
19Qwen3.8-Max1,493.8178
20Muse Spark 1.3 (Max)1,493.0834
21Muse Spark1,492.7927
22GPT-5.4 (High)1,492.6335
23GPT-5.6 Sol (xHigh)1,489.8353
24Claude Fable 5.1 (Max)1,488.552
25Gemini 3.7 Flash (High)1,487.8763
26Gemini 3.6 Flash (High)1,487.8441
27GPT-5.5 (High)1,487.2277
28Claude Opus 5 (High)1,486.5671
29Claude Opus 5 (Max)1,486.2776
30Claude Opus 4.5 (High, 32K, 20251101)1,485.321
31Claude Opus 4.5 (20251101)1,484.0978
32GPT-6 Astra (Max)1,483.9747
33GPT-5.51,483.9138
34Grok 4.20 Beta 11,483.2421
35GPT-5.5 Instant1,482.555
36Gemini 3 Flash1,481.7016
37Qwen3.7-Max-Preview1,481.5747
38Claude Sonnet 4.61,480.7062
39Gemini 3.5 Flash (High)1,480.424
40GPT-5.41,480.1879
41MiMo-V2.5-Pro1,479.9297
42GPT-6.1 Sol (Max)1,478.6794
43Grok 4.20 Beta (Reasoning, 0309)1,478.5592
44GLM-5.11,478.2538
45GLM-5.3 (Max)1,478.1891
46Gemini 3.5 Flash (Medium)1,477.9113
47Qwen3.5-Max-Preview1,477.2879
48Claude Sonnet 4.5 (20250929)1,477.2094
49Claude Sonnet 5.5 (xHigh)1,476.6015
50GLM-5.2 (Max)1,476.1321