← Arena leaderboards

Text · Factuality · Longer Query

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,538.9284
2Gemini 4 Argon (High)1,531.9889
3Claude Opus 5.5 (High)1,529.4837
4Claude Fable 5.1 (Max)1,518.7263
5Claude Opus 4.6 (High)1,512.9099
6Claude Opus 4.61,510.0541
7Claude Opus 5 (Max)1,506.7905
8Claude Fable 5 (High)1,504.5552
9Muse Wonder (Max)1,504.4414
10MiMo-V2.6-Pro1,502.4077
11GPT-5.5 (High)1,500.4176
12Claude Opus 5 (High)1,499.7098
13Claude Opus 4.7 (High)1,499.6172
14Claude Sonnet 5.5 (xHigh)1,498.7254
15GPT-5.51,498.0313
16Gemini 3.8 Flash (High)1,495.4141
17Qwen3.7-Max-Preview1,495.1444
18GPT-5.6 Sol (xHigh)1,494.5721
19Claude Opus 4.71,494.2579
20Kimi K3 (Max)1,493.9895
21Gemini 3.7 Flash (High)1,491.9528
22Claude Opus 4.8 (High)1,491.9428
23Qwen3.5-Max-Preview1,491.4024
24GPT-5.4 (High)1,491.3422
25Claude Opus 4.5 (20251101)1,490.9688
26Muse Spark 1.3 (Max)1,490.8474
27Gemini 3.5 Flash (High)1,490.32
28Claude Opus 4.5 (High, 32K, 20251101)1,488.8773
29Claude Opus 4.81,488.316
30Qwen3.8-Max1,487.7374
31Claude Sonnet 4.5 (High, 32K, 20250929)1,487.2254
32GPT-5.41,487.1053
33Claude Sonnet 4.5 (20250929)1,486.3203
34Muse Spark 1.2 (xHigh)1,486.1978
35MiMo-V2.5-Pro1,485.9803
36Gemini 3 Pro1,485.7868
37Claude Sonnet 4.61,485.0882
38DeepSeek-V4.1-Flash-20260910 (Max)1,484.4043
39GLM-5.2 (Max)1,484.2259
40GLM-5.3 (Max)1,483.9447
41Gemini 3.1 Pro Preview1,483.741
42GPT-6.1 Sol (Max)1,483.2906
43GLM-5.3-Flash1,482.9208
44Grok 4.51,481.8865
45GPT-6 Astra (Max)1,481.6912
46Gemini 3.6 Flash (High)1,480.8915
47Gemini 3.5 Flash (Medium)1,479.0412
48GPT-5.6 Terra (xHigh)1,476.7366
49Kimi K2.61,476.3795
50GLM-5.11,476.2468