← Arena leaderboards

Text · Style Control · Spanish

Arena · 50 models

RankModelScore
1Claude Fable 5 (High)1,499.3901
2Claude Opus 4.7 (High)1,498.3799
3Claude Opus 4.61,498.1669
4Claude Fable 5.1 (Max)1,497.8056
5Gemini 4 Argon (High)1,496.0859
6Muse Spark 1.2 (xHigh)1,495.921
7Claude Opus 4.6 (High)1,494.145
8Claude Opus 5 (Max)1,487.8976
9Claude Opus 5.5 (High)1,487.8251
10Muse Spark 1.3 (Max)1,485.8303
11GPT-5.5 Instant1,485.3823
12Kimi K3 (Max)1,484.5738
13Gemini 3.7 Flash (High)1,484.2067
14Gemini 3.1 Pro Preview1,482.2671
15Gemini 3.8 Flash (High)1,480.1424
16Claude Opus 4.8 (High)1,479.9452
17Claude Opus 5 (High)1,479.7697
18Muse Spark1,479.0856
19GLM-5.2 (Max)1,478.4021
20Gemini 3 Flash1,478.0344
21Claude Opus 4.5 (High, 32K, 20251101)1,476.5432
22Gemini 3.6 Flash (High)1,476.1418
23Claude Opus 4.71,474.6509
24GPT-6.1 Sol (Max)1,474.5981
25Qwen3.8-Max1,474.4137
26GPT-5.2 Chat (20260210)1,473.9774
27Gemini 3.5 Flash (High)1,473.5554
28Gemini 3 Pro1,473.2845
29Muse Spark 1.11,473.1472
30GLM-5.3-Flash1,472.076
31Hy31,471.952
32GPT-5.5 (High)1,470.9078
33Gemini 3.5 Flash (Medium)1,470.7245
34Dola Seed 2.0 Pro1,470.3333
35ERNIE-5.0-Preview (1203)1,470.2048
36Muse Wonder (Max)1,470.0709
37GLM-5.3 (Max)1,468.7811
38Claude Opus 4.81,468.727
39Claude Opus 4.1 (20250805)1,467.9041
40Grok 4.20 Beta 11,467.6768
41Claude Sonnet 4.5 (20250929)1,466.1962
42Grok 4.1 (Thinking)1,465.9837
43Claude Opus 4.1 (Thinking 16K, 20250805)1,465.8942
44Claude Sonnet 4.61,465.5961
45GPT-5.6 Sol (xHigh)1,465.3784
46Grok 4.20 Multi-Agent Beta (0309)1,464.9921
47GLM-5.11,464.8995
48Claude Opus 4.5 (20251101)1,464.5489
49DeepSeek-V4.1-Flash-20260910 (Max)1,463.3868
50GPT-5.6 Luna (xHigh)1,462.5507