← Arena leaderboards

Text · Factuality · Medicine & Healthcare

Arena · 50 models

RankModelScore
1Gemini 4 Argon (High)1,536.0971
2Claude Opus 5.5 (High)1,533.104
3Claude Opus 5 (Max)1,525.8885
4Qwen3.5-Max-Preview1,525.4609
5Claude Fable 5.1 (Max)1,522.5042
6Gemini 3 Pro1,518.8117
7Claude Opus 4.6 (High)1,518.0935
8Claude Opus 5 (High)1,518.0382
9Kimi K3 (Max)1,516.233
10Claude Opus 4.71,514.9976
11DeepSeek-V4.1-Flash-20260910 (Max)1,514.1656
12Qwen3.8-Max1,512.8489
13Claude Opus 4.61,512.8144
14Claude Opus 4.7 (High)1,510.7241
15Gemini 3.8 Flash (High)1,508.7728
16Gemini 3.5 Flash (High)1,506.2873
17Claude Fable 5 (High)1,504.7488
18Muse Spark 1.3 (Max)1,504.7033
19GPT-5.5 (High)1,503.6883
20Gemini 2.5 Pro1,502.5007
21ERNIE 5.11,502.254
22GPT-5.4 (High)1,501.5717
23GPT-5.51,501.2395
24MiMo-V2.5-Pro1,500.7569
25Claude Opus 4.8 (High)1,500.2995
26Gemini 3.7 Flash (High)1,499.8951
27Gemini 3.1 Pro Preview1,499.7982
28GLM-5.3 (Max)1,498.723
29Gemini 3.5 Flash (Medium)1,498.704
30GLM-5.2 (Max)1,498.0864
31Muse Spark 1.11,497.9496
32GLM-5.3-Flash1,495.7839
33GLM-5.11,494.6409
34GLM-4.61,493.8732
35GPT-5.1 (High)1,492.4396
36Claude Opus 4.81,491.4014
37GPT-5.41,491.2243
38DeepSeek-V4-Pro1,488.2748
39Gemini 3.6 Flash (High)1,488.1596
40Qwen3.7-Plus1,487.382
41DeepSeek-V4-Pro Preview (High)1,487.3482
42Grok 4.20 Beta (Reasoning, 0309)1,487.1365
43Gemini 3 Flash1,485.7921
44GPT-5.11,485.6697
45GPT-5.6 Terra (xHigh)1,484.9535
46Kimi K2.61,483.9166
47Qwen3.5-397B-A17B1,483.5503
48Grok 4.20 Multi-Agent Beta (0309)1,483.3344
49Inkling1,483.163
50ChatGPT-4o Latest (20250326)1,482.9123