← Arena leaderboards

Text · Medicine & Healthcare

Arena · 50 models

RankModelScore
1Gemini 4 Argon (High)1,543.5619
2Claude Fable 5.1 (Max)1,535.1364
3Gemini 4 Carbon (High)1,527.3237
4Claude Opus 5 (Max)1,526.3721
5Muse Wonder (Max)1,513.8934
6Claude Opus 5 (High)1,511.7095
7Claude Opus 5.5 (High)1,510.4867
8Gemini 3.8 Flash (High)1,506.1785
9Qwen3.8-Max1,504.6627
10Claude Opus 4.6 (High)1,503.9707
11Qwen3.5-Max-Preview1,497.8342
12Gemini 3.7 Flash (High)1,497.3547
13Claude Opus 4.61,497.2775
14Claude Opus 4.7 (High)1,495.3312
15MiMo-V2.6-Pro1,494.7515
16Muse Spark 1.2 (xHigh)1,493.9227
17Muse Spark 1.3 (Max)1,492.9506
18Gemini 3 Pro1,491.7759
19Claude Opus 4.71,490.4411
20Kimi K3 (Max)1,487.2913
21ERNIE 5.11,487.2042
22DeepSeek-V4.1-Flash-20260910 (Max)1,486.1165
23Gemini 3.1 Pro Preview1,485.7466
24Gemini 3.5 Flash (High)1,483.5611
25GLM-5.3 (Max)1,482.6706
26Gemini 3.5 Flash (Medium)1,482.5765
27Muse Spark 1.11,480.1717
28Qwen3.7-Max-Preview1,480.1194
29Claude Fable 5 (High)1,480.0059
30GLM-5.3-Flash1,477.8455
31Claude Sonnet 5.5 (xHigh)1,476.1077
32Gemini 2.5 Pro1,475.9574
33Muse Spark1,475.4742
34GLM-5.2 (Max)1,475.0212
35GLM-5.11,473.7325
36MiMo-V2.5-Pro1,472.4686
37ERNIE-5.0-Preview (1203)1,471.4395
38Dola Seed 2.0 Pro1,469.9323
39GLM-4.71,468.6119
40Grok 3 Preview (02-24)1,468.5545
41Gemini 3.6 Flash (High)1,468.4801
42DeepSeek-V3.2-Exp (Thinking)1,468.4266
43DeepSeek-V3.1-Terminus (Thinking)1,468.2493
44DeepSeek-V4-Pro Preview (High)1,468.236
45Qwen3-Max-Preview1,467.523
46DeepSeek-V4-Pro1,465.5501
47GPT-5.51,465.1111
48Qwen3.7-Plus1,465.0278
49amazon-nova-experimental-chat (12-10)1,464.2059
50Claude Opus 4.8 (High)1,464.1587