Skip to content

Benchmark

Arena ELO Text Factuality - Industry Medicine and Healthcare

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

Models measured
113
Scores recorded
128
Sources
1
IQ weight
2.07

Score distribution

1,475.5
Mean
1,474.9
Median
28.4
Std dev
1,444.2
10th percentile
1,511.8
90th percentile
1,365.9
Min
1,365.91,540.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.07 for chat models, measured over 113 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 data1,540.5
2Claude Opus 5.5High· LMArena data1,528.2
3Claude Opus 5Max· LMArena data1,527.6
4Claude Fable 5.1Max· LMArena data1,525.9
5Qwen3.5-Max-Preview· LMArena data1,524.5
6Muse WonderMax· LMArena data1,518.6
7Qwen3.8 Max· LMArena data1,518.3
8Gemini 3 Pro Preview· LMArena data1,518.2
9Claude Opus 4.6High· LMArena data1,518.1
10DeepSeek V4.1 Flash 0910Max· LMArena data1,516.8
11Claude Opus 5High· LMArena data1,516.5
12Claude Opus 4.7· LMArena data1,514.1
13Claude Opus 4.6· LMArena data1,513
14Kimi K3Max· LMArena data1,511.8
15Claude Opus 4.7High· LMArena data1,510.4
16Muse Spark 1.3Max· LMArena data1,508.6
17Gemini 3.8 FlashHigh· LMArena data1,507.8
18Gemini 3.5 FlashHigh· LMArena data1,505.2
19Claude Fable 5High· LMArena data1,504.4
20GLM 5.3Max· LMArena data1,503.2
21ERNIE 5.1· LMArena data1,503
22GPT 5.5High· LMArena data1,502.9
23Gemini 3.7 FlashHigh· LMArena data1,502.1
24GPT 5.4High· LMArena data1,501.7
25Gemini 2.5 Pro· LMArena data1,501.1
26Claude Opus 4.8High· LMArena data1,500.9
27GPT 5.5· LMArena data1,500.5
28MiMo V2.5 Pro· LMArena data1,499.6
29Gemini 3.5 FlashMedium· LMArena data1,499.6
30Gemini 3.1 Pro Preview· LMArena data1,498.5
31Muse Spark 1.1· LMArena data1,498.2
32GLM 5.2Max· LMArena data1,497.6
33GLM 5.1· LMArena data1,495.2
34GPT-6.1 SolMax· LMArena data1,494.7
35GLM 5.3 Flash· LMArena data1,493.9
36GLM 4.6· LMArena data1,493.8
37GPT 5.4· LMArena data1,492
38GPT 5.1High· LMArena data1,490.5
39Muse Spark 1.2xHigh· LMArena data1,490.1
40Gemini 3.6 FlashHigh· LMArena data1,489.1
41Claude Opus 4.8· LMArena data1,488.6
42Grok 4.20Reasoning, 0309, beta· LMArena data1,487.5
43DeepSeek V4 Pro· LMArena data1,486.8
44Qwen3.7 Plus· LMArena data1,486.7
45DeepSeek-V4-Pro PreviewHigh· LMArena data1,486.7
46GPT 5.1· LMArena data1,486.4
47Gemini 3 Flash· LMArena data1,485.7
48ChatGPT-4o Latest20250326· LMArena data1,483.9
49Grok 4.20 Multi-Agent0309, beta· LMArena data1,483.3
50Kimi K2.6· LMArena data1,482.9

Showing 1–50 of 128 results.

Data credits: LMArena, CC BY 4.0 (licence)