← Arena leaderboards

Text · Multi Turn

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,564.6757
2Gemini 4 Argon (High)1,541.7713
3Claude Opus 4.6 (High)1,512.1634
4Claude Opus 4.61,505.5736
5Claude Opus 4.7 (High)1,505.2635
6Muse Wonder (Max)1,505.0678
7Claude Opus 4.71,503.9836
8Gemini 3.8 Flash (High)1,503.6679
9Claude Fable 5 (High)1,503.4201
10Claude Opus 5.5 (High)1,500.2021
11Claude Opus 5 (Max)1,498.8192
12Muse Spark 1.2 (xHigh)1,496.1595
13Claude Fable 5.1 (Max)1,495.3761
14Claude Opus 5 (High)1,494.3237
15Qwen3.8-Max1,491.0275
16Kimi K3 (Max)1,489.573
17Muse Spark 1.3 (Max)1,487.8775
18Gemini 3.1 Pro Preview1,486.2639
19Gemini 3.7 Flash (High)1,484.862
20Gemini 3 Pro1,484.0487
21Muse Spark 1.11,483.7986
22GPT-5.4 (High)1,481.7923
23Gemini 3.6 Flash (High)1,481.2603
24Gemini 3.5 Flash (High)1,480.9541
25Qwen3.7-Max-Preview1,479.8588
26Qwen3.5-Max-Preview1,477.7503
27Muse Spark1,476.6979
28Gemini 3.5 Flash (Medium)1,475.9712
29GPT-5.5 (High)1,475.9202
30Claude Opus 4.8 (High)1,475.7005
31MiMo-V2.5-Pro1,475.5101
32GLM-5.11,472.3978
33Claude Opus 4.81,472.3672
34GPT-5.51,472.3471
35Gemini 3 Flash1,471.0894
36GLM-5.3-Flash1,471.052
37ERNIE 5.11,470.3442
38GLM-5.3 (Max)1,470.0073
39GLM-5.2 (Max)1,469.0457
40Claude Sonnet 5.5 (xHigh)1,468.1139
41DeepSeek-V4-Pro1,467.4295
42Claude Opus 4.5 (20251101)1,466.0948
43MiMo-V2.6-Pro1,465.551
44Claude Sonnet 4.5 (20250929)1,464.6355
45GPT-5.41,463.3168
46Claude Sonnet 4.61,463.2079
47GPT-5.6 Sol (xHigh)1,461.2232
48DeepSeek-V4.1-Flash-20260910 (Max)1,460.2626
49Claude Opus 4.5 (High, 32K, 20251101)1,460.2482
50Qwen3.7-Plus1,459.3399