← Arena leaderboards

Text · Factuality · Life & Physical & Social Science

Arena · 50 models

RankModelScore
1Claude Fable 5.1 (Max)1,529.9293
2Gemini 4 Argon (High)1,528.4887
3Claude Opus 5 (Max)1,528.2543
4Claude Opus 5.5 (High)1,527.5627
5Claude Opus 4.6 (High)1,520.6425
6Muse Wonder (Max)1,517.5661
7Claude Opus 5 (High)1,513.6531
8Claude Fable 5 (High)1,513.3874
9Qwen3.5-Max-Preview1,512.5331
10Qwen3.8-Max1,511.9396
11Claude Opus 4.61,511.6808
12Gemini 3.7 Flash (High)1,509.7276
13Kimi K3 (Max)1,509.1111
14Gemini 3.8 Flash (High)1,508.6972
15GPT-5.51,506.8667
16GPT-5.5 (High)1,506.5463
17Claude Opus 4.7 (High)1,504.83
18Gemini 3.5 Flash (High)1,504.4325
19Muse Spark 1.3 (Max)1,502.64
20Claude Opus 4.71,500.0983
21Gemini 3 Pro1,499.8373
22GPT-5.4 (High)1,499.2172
23Muse Spark 1.2 (xHigh)1,498.6363
24GLM-5.3 (Max)1,498.5841
25Claude Opus 4.8 (High)1,497.1248
26Claude Sonnet 5.5 (xHigh)1,496.4966
27Gemini 3.1 Pro Preview1,495.6783
28Gemini 3.5 Flash (Medium)1,494.9271
29DeepSeek-V4.1-Flash-20260910 (Max)1,492.8752
30GLM-5.2 (Max)1,491.7587
31Gemini 2.5 Pro1,491.2962
32Gemini 3.6 Flash (High)1,491.2231
33MiMo-V2.5-Pro1,490.8473
34Claude Opus 4.81,489.5222
35GPT-6 Astra (Max)1,489.2837
36GPT-6.1 Sol (Max)1,489.2657
37Grok 4.51,488.8614
38GPT-5.41,488.8597
39GLM-5.3-Flash1,488.1406
40GPT-5.6 Sol (xHigh)1,487.9558
41Claude Sonnet 4.61,486.3111
42Qwen3-Max-Preview1,485.121
43GLM-5.11,485.0928
44GPT-5.6 Terra (xHigh)1,484.5962
45Muse Spark1,484.3666
46Gemini 3 Flash1,483.6039
47DeepSeek-V4-Pro1,482.8926
48Muse Spark 1.11,482.2134
49ERNIE 5.11,482.164
50DeepSeek-V4-Pro (High, 20260813)1,482.1555