Skip to content

Benchmark

Arena ELO - Industry Medicine and Healthcare

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
336
Scores recorded
391
Sources
1
IQ weight
1.38

Score distribution

1,319.8
Mean
1,368.4
Median
152.6
Std dev
1,071.7
10th percentile
1,469.7
90th percentile
819.1
Min
819.11,538.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.38 for chat models, measured over 336 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 ArgonHigh· LMArena data1,538.2
2Gemini 4 CarbonHigh· LMArena data1,534.1
3Gemini 4 NeonHigh· LMArena data1,533.7
4Claude Fable 5.1Max· LMArena data1,528.9
5Claude Opus 5Max· LMArena data1,525.8
6Claude Opus 5.5High· LMArena data1,514.7
7Qwen3.8 Max· LMArena data1,512
8Claude Opus 5High· LMArena data1,509
9Gemini 3.8 FlashHigh· LMArena data1,505.4
10Claude Opus 4.6High· LMArena data1,503.8
11Gemini 3.7 FlashHigh· LMArena data1,500.1
12Muse WonderMax· LMArena data1,500.1
13Qwen3.5-Max-Preview· LMArena data1,497.4
14Claude Opus 4.6· LMArena data1,497.2
15Claude Opus 4.7High· LMArena data1,495.5
16MiMo V2.6 Pro· LMArena data1,493.5
17Muse Spark 1.3Max· LMArena data1,492.9
18Muse Spark 1.2xHigh· LMArena data1,492.6
19Gemini 3 Pro Preview· LMArena data1,492.5
20Claude Opus 4.7· LMArena data1,490.3
21DeepSeek V4.1 Flash 0910Max· LMArena data1,489.6
22ERNIE 5.1· LMArena data1,487.9
23Gemini 3.1 Pro Preview· LMArena data1,486.3
24Kimi K3Max· LMArena data1,484.6
25Gemini 3.5 FlashHigh· LMArena data1,484.2
26Gemini 3.5 FlashMedium· LMArena data1,482.9
27GLM 5.3Max· LMArena data1,481.2
28Muse Spark 1.1· LMArena data1,480.5
29Qwen3.7 Max Preview· LMArena data1,480.5
30Claude Fable 5High· LMArena data1,480
31Gemini 4 HydrogenHigh· LMArena data1,480
32Gemini 2.5 Pro· LMArena data1,476.2
33GLM 5.2Max· LMArena data1,476.2
34GLM 5.3 Flash· LMArena data1,476
35GLM 5.1· LMArena data1,473.7
36Muse Spark· LMArena data1,473
37MiMo V2.5 Pro· LMArena data1,472.4
38ERNIE-5.0-Preview1203· LMArena data1,471.3
39Doubao Seed 2.0 Pro· LMArena data1,470.4
40Gemini 3.6 FlashHigh· LMArena data1,469.7
41GLM 4.7· LMArena data1,469.3
42Grok 3 Preview02-24· LMArena data1,468.5
43DeepSeek-V4-Pro PreviewHigh· LMArena data1,468.4
44DeepSeek V3.2 ExpThinking· LMArena data1,468.2
45Qwen3 Max Preview· LMArena data1,468
46DeepSeek V3.1 TerminusThinking· LMArena data1,467.8
47Qwen3.7 Plus· LMArena data1,466
48Claude Opus 4.8High· LMArena data1,465.2
49GPT 5.5· LMArena data1,465
50DeepSeek V4 Pro· LMArena data1,464.3

Showing 1–50 of 391 results.

Data credits: LMArena, CC BY 4.0 (licence)