← Arena leaderboards

Text · Factuality · English

Arena · 50 models

RankModelScore
1Claude Opus 5.5 (High)1,519.191
2Gemini 4 Carbon (High)1,517.2514
3Gemini 4 Argon (High)1,509.1552
4Muse Wonder (Max)1,505.8367
5Claude Opus 4.6 (High)1,503.9867
6Claude Fable 5.1 (Max)1,501.9261
7Claude Opus 4.61,499.9275
8MiMo-V2.6-Pro1,497.3737
9Claude Opus 5 (Max)1,494.5532
10Claude Fable 5 (High)1,493.7301
11Muse Spark 1.3 (Max)1,490.176
12Muse Spark 1.2 (xHigh)1,489.8738
13Claude Sonnet 5.5 (xHigh)1,489.5652
14Claude Opus 5 (High)1,488.2751
15GPT-5.51,487.435
16Claude Opus 4.7 (High)1,487.3758
17GPT-5.4 (High)1,487.3615
18GPT-5.5 (High)1,487.3483
19Qwen3.8-Max1,487.0456
20Qwen3.5-Max-Preview1,483.737
21Claude Opus 4.71,483.1823
22Kimi K3 (Max)1,482.9109
23Gemini 3 Pro1,482.4218
24Gemini 3.5 Flash (High)1,482.3506
25DeepSeek-V4.1-Flash-20260910 (Max)1,481.7453
26MiMo-V2.5-Pro1,480.5054
27GPT-5.6 Sol (xHigh)1,479.5982
28Gemini 3.6 Flash (High)1,479.3745
29Gemini 3.7 Flash (High)1,479.3025
30Claude Opus 4.8 (High)1,479.0284
31GPT-5.41,478.9649
32Muse Spark1,478.8392
33GLM-5.3 (Max)1,478.8339
34GPT-6.1 Sol (Max)1,477.3829
35Claude Sonnet 4.61,476.9774
36Qwen3.7-Max-Preview1,476.8069
37Gemini 3.1 Pro Preview1,476.0975
38Gemini 3.8 Flash (High)1,475.9756
39GPT-5.6 Terra (xHigh)1,474.3777
40GPT-6 Luna (Max)1,473.4798
41Gemini 3.5 Flash (Medium)1,473.0721
42GLM-5.2 (Max)1,472.7852
43GLM-5.11,472.7738
44Claude Opus 4.81,472.6116
45Grok 4.51,472.4822
46GPT-6 Astra (Max)1,472.4027
47MiMo-V2.6-Flash1,472.3725
48Muse Spark 1.11,471.2867
49GPT-5.6 Luna (xHigh)1,471.0787
50Gemini 3 Flash1,471.065