← Arena leaderboards

Text · Style Control · Medicine & Healthcare

Arena · 50 models

RankModelScore
1Gemini 4 Argon (High)1,539.3281
2Muse Wonder (Max)1,529.5861
3Claude Fable 5.1 (Max)1,528.4356
4Gemini 4 Carbon (High)1,517.9726
5Claude Opus 4.7 (High)1,516.9783
6Claude Opus 4.6 (High)1,516.8533
7Claude Opus 5 (Max)1,513.4026
8Kimi K3 (Max)1,512.3688
9Claude Opus 5.5 (High)1,512.288
10Claude Opus 4.71,512.1134
11Claude Opus 4.61,510.9336
12Qwen3.8-Max1,510.4851
13Muse Spark 1.2 (xHigh)1,510.4223
14Gemini 3 Pro1,508.9883
15Gemini 3.8 Flash (High)1,508.0855
16DeepSeek-V4.1-Flash-20260910 (Max)1,507.9353
17Claude Opus 5 (High)1,505.9836
18Claude Fable 5 (High)1,505.5323
19Gemini 3.1 Pro Preview1,504.4534
20Gemini 3.7 Flash (High)1,504.3174
21GLM-5.3 (Max)1,501.5449
22Muse Spark 1.11,500.8798
23Muse Spark 1.3 (Max)1,500.3694
24Claude Opus 4.8 (High)1,499.9593
25Grok 4.1 (Thinking)1,499.7647
26Muse Spark1,498.648
27Grok 4.20 Beta 11,497.8926
28Claude Opus 4.81,497.7968
29GPT-5.2 Chat (20260210)1,497.3607
30ERNIE 5.11,492.7872
31GLM-5.3-Flash1,492.4051
32Claude Sonnet 5.5 (xHigh)1,491.7254
33GLM-5.2 (Max)1,491.7111
34Qwen3.5-Max-Preview1,491.2689
35MiMo-V2.6-Pro1,490.1118
36Dola Seed 2.0 Pro1,489.6409
37ERNIE-5.0-Preview (1203)1,489.4563
38Gemini 3.5 Flash (Medium)1,487.986
39Claude Opus 4.5 (High, 32K, 20251101)1,487.7499
40Claude Sonnet 4.61,487.1154
41GLM-4.71,487.0247
42Claude Opus 4.5 (20251101)1,486.8291
43GPT-5.5 Instant1,486.8288
44Qwen3.7-Max-Preview1,486.6005
45Grok 4.20 Beta (Reasoning, 0309)1,486.5049
46GPT-5.51,486.3843
47Qwen3.6-Max-Preview1,485.7459
48MiMo-V2.5-Pro1,485.6456
49GLM-5.11,485.4515
50Gemini 3.5 Flash (High)1,485.0711