← Arena leaderboards

Text · Factuality · Entertainment & Sports & Media

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,503.5497
2Gemini 4 Argon (High)1,499.4189
3Claude Opus 5.5 (High)1,497.6972
4Claude Fable 5.1 (Max)1,488.1744
5Claude Opus 4.6 (High)1,482.9147
6Muse Wonder (Max)1,480.7053
7Claude Fable 5 (High)1,474.1987
8Claude Opus 5 (Max)1,469.5007
9Claude Opus 4.61,469.0283
10Gemini 3.7 Flash (High)1,466.0244
11Claude Opus 4.7 (High)1,463.9782
12Gemini 3.8 Flash (High)1,463.9399
13Gemini 3 Pro1,463.239
14Claude Opus 5 (High)1,463.2339
15Claude Opus 4.71,462.8166
16Qwen3.5-Max-Preview1,462.5628
17Gemini 3.5 Flash (High)1,462.1876
18Qwen3.8-Max1,461.64
19GPT-5.6 Sol (xHigh)1,460.4401
20Claude Sonnet 5.5 (xHigh)1,459.6386
21MiMo-V2.6-Pro1,459.3103
22Gemini 3.1 Pro Preview1,459.0193
23GPT-5.51,458.2392
24Muse Spark 1.3 (Max)1,457.7669
25GPT-5.5 (High)1,456.4111
26Gemini 3.6 Flash (High)1,455.378
27Gemini 3.5 Flash (Medium)1,453.9803
28GPT-5.4 (High)1,452.9193
29Muse Spark1,450.7186
30Kimi K3 (Max)1,450.2951
31DeepSeek-V4.1-Flash-20260910 (Max)1,449.5291
32Gemini 3 Flash1,449.2042
33Claude Opus 4.8 (High)1,449.113
34Muse Spark 1.2 (xHigh)1,448.2214
35GLM-5.3 (Max)1,447.1804
36GPT-6 Astra (Max)1,446.5617
37GLM-5.2 (Max)1,446.0612
38GPT-6.1 Sol (Max)1,445.2936
39Grok 4.51,445.1677
40Claude Opus 4.81,444.4157
41Claude Opus 4.5 (20251101)1,444.4129
42MiMo-V2.5-Pro1,441.9386
43GLM-5.11,441.3391
44GPT-5.41,440.788
45Claude Sonnet 4.61,440.0377
46Claude Sonnet 4.5 (20250929)1,439.9674
47Gemini 2.5 Pro1,438.7654
48GLM-5.3-Flash1,438.5279
49GLM-51,437.5784
50Claude Opus 4.5 (High, 32K, 20251101)1,437.2031