← Arena leaderboards

Text · Style Control · Entertainment & Sports & Media

Arena · 50 models

RankModelScore
1Gemini 4 Argon (High)1,511.7537
2Gemini 4 Carbon (High)1,508.8543
3Claude Opus 5.5 (High)1,501.4587
4Claude Fable 5 (High)1,492.9264
5Claude Opus 4.6 (High)1,491.1293
6Muse Wonder (Max)1,486.8181
7Claude Opus 4.7 (High)1,480.397
8Claude Fable 5.1 (Max)1,479.5139
9Gemini 3.8 Flash (High)1,478.4408
10Gemini 3.7 Flash (High)1,476.66
11Claude Opus 4.61,475.5039
12Claude Opus 4.71,472.835
13GPT-5.6 Sol (xHigh)1,470.769
14Gemini 3.1 Pro Preview1,469.9167
15Gemini 3 Pro1,469.3082
16Claude Opus 5 (High)1,463.9293
17Claude Opus 5 (Max)1,462.5039
18Claude Sonnet 5.5 (xHigh)1,461.6177
19Muse Spark1,461.4931
20Kimi K3 (Max)1,461.4841
21Gemini 3.6 Flash (High)1,461.2147
22Muse Spark 1.3 (Max)1,460.8658
23Claude Opus 4.8 (High)1,460.1838
24Qwen3.8-Max1,459.5117
25GPT-6.1 Sol (Max)1,459.0699
26Gemini 3.5 Flash (Medium)1,457.8746
27GPT-6 Astra (Max)1,457.4618
28Claude Opus 4.5 (High, 32K, 20251101)1,456.0814
29Gemini 3.5 Flash (High)1,454.2073
30Claude Opus 4.5 (20251101)1,454.1764
31Claude Opus 4.81,453.7031
32Gemini 3 Flash1,453.6511
33GPT-5.5 Instant1,451.1248
34DeepSeek-V4.1-Flash-20260910 (Max)1,449.9233
35Muse Spark 1.2 (xHigh)1,449.8106
36GLM-5.3 (Max)1,449.0796
37GPT-5.5 (High)1,448.5271
38Grok 4.20 Beta 11,448.2751
39Muse Spark 1.11,447.8911
40GPT-5.51,447.7071
41MiMo-V2.6-Pro1,447.1839
42GLM-5.2 (Max)1,445.6462
43Claude Sonnet 4.5 (High, 32K, 20250929)1,445.5289
44Grok 4.51,445.5084
45Claude Sonnet 4.61,445.3515
46Grok 4.20 Beta (Reasoning, 0309)1,444.9688
47Claude Sonnet 4.5 (20250929)1,443.4734
48Qwen3.5-Max-Preview1,443.0898
49GLM-5.11,441.1454
50GPT-5.4 (High)1,441.1244