← Arena leaderboards

Text · Factuality · Software & It Services

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,548.8782
2Claude Opus 5.5 (High)1,548.5944
3Gemini 4 Argon (High)1,538.114
4Claude Fable 5.1 (Max)1,537.3554
5Claude Opus 4.61,533.0793
6Claude Opus 4.6 (High)1,532.7045
7MiMo-V2.6-Pro1,530.161
8Muse Wonder (Max)1,527.4808
9Claude Opus 5 (Max)1,527.1427
10GPT-5.5 (High)1,522.6162
11Claude Sonnet 5.5 (xHigh)1,520.7229
12Claude Opus 5 (High)1,520.1997
13Muse Spark 1.2 (xHigh)1,519.8817
14Claude Fable 5 (High)1,519.8333
15GPT-5.4 (High)1,519.3802
16Claude Opus 4.7 (High)1,519.1856
17GPT-5.6 Sol (xHigh)1,518.2066
18GPT-5.51,516.7824
19Muse Spark 1.3 (Max)1,515.8773
20Qwen3.7-Max-Preview1,515.1705
21Claude Opus 4.71,513.0626
22GPT-6.1 Sol (Max)1,512.9973
23Kimi K3 (Max)1,512.1632
24GPT-6 Astra (Max)1,512.058
25GPT-5.6 Terra (xHigh)1,511.4574
26GPT-5.41,511.063
27GPT-6 Luna (Max)1,509.745
28Gemini 3.7 Flash (High)1,509.3581
29DeepSeek-V4.1-Flash-20260910 (Max)1,509.3036
30Claude Opus 4.8 (High)1,509.2918
31MiMo-V2.5-Pro1,509.2144
32Gemini 3.5 Flash (High)1,508.9247
33Qwen3.8-Max1,507.1098
34Gemini 3 Pro1,506.8138
35Claude Sonnet 4.61,506.7681
36GLM-5.3-Flash1,506.764
37Gemini 3.6 Flash (High)1,506.5228
38Qwen3.5-Max-Preview1,505.6501
39Gemini 3.8 Flash (High)1,505.434
40MiMo-V2.6-Flash1,504.8565
41Claude Opus 4.5 (20251101)1,504.1392
42Claude Opus 4.81,504.0425
43GLM-5.3 (Max)1,503.753
44Claude Opus 4.5 (High, 32K, 20251101)1,503.3819
45Muse Spark 1.11,502.6011
46Grok 4.51,500.9981
47GPT-5.6 Luna (xHigh)1,499.7992
48GLM-5.2 (Max)1,499.4028
49Gemini 3.5 Flash (Medium)1,499.3341
50Kimi K2.61,498.7434