← Arena leaderboards

Text · Style Control · Business & Management & Financial Operations

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,514.7622
2Gemini 4 Argon (High)1,512.4283
3Claude Opus 4.7 (High)1,508.0415
4Muse Wonder (Max)1,501.8697
5Muse Spark 1.2 (xHigh)1,501.1064
6Claude Fable 5 (High)1,500.9996
7Claude Opus 4.6 (High)1,499.5267
8Claude Opus 4.61,498.7101
9Muse Spark 1.3 (Max)1,497.7954
10Claude Opus 5.5 (High)1,495.2694
11Claude Opus 4.71,494.9358
12Muse Spark 1.11,491.1216
13GPT-5.5 (High)1,490.0269
14Muse Spark1,489.4499
15Claude Opus 4.8 (High)1,489.1576
16Kimi K3 (Max)1,487.4109
17Claude Fable 5.1 (Max)1,486.9266
18GPT-6.1 Sol (Max)1,486.6702
19Claude Opus 5 (High)1,486.252
20Claude Opus 4.81,486.0214
21GPT-5.6 Sol (xHigh)1,485.7032
22GPT-5.51,485.1352
23Gemini 3.7 Flash (High)1,484.9705
24GPT-5.2 Chat (20260210)1,484.5343
25Qwen3.8-Max1,484.2635
26Claude Opus 5 (Max)1,483.6899
27GPT-5.4 (High)1,481.8667
28Gemini 3.8 Flash (High)1,481.7903
29Claude Sonnet 4.61,481.5589
30DeepSeek-V4.1-Flash-20260910 (Max)1,477.5624
31Gemini 3.1 Pro Preview1,477.4684
32GPT-5.5 Instant1,475.7673
33ERNIE 5.11,474.9227
34GLM-5.3 (Max)1,474.8708
35Claude Sonnet 5.5 (xHigh)1,474.5848
36GPT-5.41,474.2682
37Gemini 3 Pro1,473.8882
38Gemini 3.6 Flash (High)1,472.6937
39GPT-6 Astra (Max)1,472.6601
40Claude Opus 4.5 (20251101)1,471.906
41MiMo-V2.5-Pro1,471.5112
42GLM-5.3-Flash1,470.3206
43Grok 4.20 Beta 11,469.0299
44Gemini 3 Flash1,468.4734
45Gemini 3.5 Flash (High)1,468.0205
46Claude Opus 4.5 (High, 32K, 20251101)1,467.1762
47DeepSeek-V4-Pro (High, 20260813)1,467.115
48GLM-5.11,466.6754
49Claude Sonnet 5 (High)1,466.163
50GPT-5.6 Terra (xHigh)1,466.1474