← Arena leaderboards

Text · Style Control · Writing & Literature & Language

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,529.4617
2Claude Opus 5.5 (High)1,519.4819
3Gemini 4 Argon (High)1,516.7929
4Claude Fable 5 (High)1,507.8295
5Claude Opus 4.6 (High)1,499.5831
6Claude Opus 4.7 (High)1,496.921
7Claude Fable 5.1 (Max)1,496.8957
8Muse Wonder (Max)1,495.8144
9Gemini 3.7 Flash (High)1,492.1359
10Gemini 3.8 Flash (High)1,491.837
11Claude Opus 4.61,488.8223
12Claude Opus 4.71,483.2855
13Gemini 3.1 Pro Preview1,482.3303
14GPT-5.6 Sol (xHigh)1,482.2513
15Claude Opus 5 (High)1,481.447
16Claude Opus 5 (Max)1,481.1322
17Gemini 3 Pro1,481.0659
18Kimi K3 (Max)1,476.8094
19Claude Opus 4.8 (High)1,475.6013
20Muse Spark 1.3 (Max)1,474.5216
21Gemini 3.5 Flash (High)1,474.4787
22Qwen3.8-Max1,474.1008
23Gemini 3.6 Flash (High)1,474.0993
24Gemini 3.5 Flash (Medium)1,472.8295
25Claude Sonnet 5.5 (xHigh)1,472.0739
26GPT-5.5 (High)1,469.1605
27GPT-6.1 Sol (Max)1,468.9185
28GLM-5.3 (Max)1,468.6823
29Claude Opus 4.81,467.7782
30Claude Opus 4.5 (20251101)1,466.458
31GPT-5.51,466.4247
32Claude Opus 4.5 (High, 32K, 20251101)1,465.8423
33GPT-6 Astra (Max)1,464.6744
34GPT-5.4 (High)1,464.0335
35Muse Spark1,461.7777
36Gemini 3 Flash1,460.9217
37GPT-5.5 Instant1,459.2671
38GLM-5.2 (Max)1,458.6159
39GPT-5.41,458.3298
40Grok 4.51,458.2043
41Muse Spark 1.11,457.3574
42Muse Spark 1.2 (xHigh)1,457.2924
43Qwen3.7-Max-Preview1,456.8412
44DeepSeek-V4.1-Flash-20260910 (Max)1,456.1512
45Claude Sonnet 4.61,455.2655
46Qwen3.5-Max-Preview1,454.6882
47DeepSeek-V4-Pro (High, 20260813)1,454.6542
48MiMo-V2.6-Pro1,454.4025
49Claude Sonnet 4.5 (20250929)1,453.8104
50GPT-5.2 Chat (20260210)1,453.3082