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
51Claude Fable 5.2Max· LMArena data1,463.8
52Gemini 3 Flash· LMArena data1,462.9
53nova-experimental-chat12-10· LMArena data1,461.6
54ERNIE 5.00110· LMArena data1,460.4
55Qwen3.6 Max Preview· LMArena data1,459.6
56LongCat Flash Chat· LMArena data1,459.3
57Claude Sonnet 5.5xHigh· LMArena data1,458.3
58GPT 5.4High· LMArena data1,458.3
59Qwen 3 235B A22B2507, thinking· LMArena data1,458.1
60Claude Opus 4.8· LMArena data1,458
61Nemotron 3 UltraNVFP4· LMArena data1,457.5
62GPT 5.5High· LMArena data1,456.7
63Qwen3 Next 80B A3B Instruct· LMArena data1,456.6
64GPT 5.1High· LMArena data1,455.9
65Kimi K2.6· LMArena data1,455.6
66Qwen3.5 397B A17B· LMArena data1,455.2
67GLM 4.6· LMArena data1,455.1
68GLM 4.5· LMArena data1,454.8
69ChatGPT-4o Latest20250326· LMArena data1,454.5
70GLM 5· LMArena data1,454.5
71Grok 4.20Reasoning, 0309, beta· LMArena data1,454.4
72Hunyuan T120250711· LMArena data1,453.8
73Grok 4.20 Multi-Agent0309, beta· LMArena data1,452.8
74Grok 4.20 Beta 1· LMArena data1,451.8
75MiMo V2.6 Flash· LMArena data1,451.5
76Claude Sonnet 4.6· LMArena data1,451.4
77DeepSeek V3.1 Terminus· LMArena data1,451.3
78Inkling FP4· LMArena data1,450.6
79Mistral Medium 3.12508· LMArena data1,450
80Gemma 4 31B IT· LMArena data1,450
81Grok 4.1Thinking· LMArena data1,449.7
82Hy3 (Deep Infra)· LMArena data1,449.1
83Kimi K2.5Thinking· LMArena data1,448.9
84OpenAI o32025-04-16· LMArena data1,447.8
85DeepSeek V4 ProHigh, 20260813· LMArena data1,447.5
86DeepSeek V4 Flash· LMArena data1,447.4
87Gemini 3 FlashMinimal· LMArena data1,447.4
88Mistral Large 3· LMArena data1,446.7
89nova-experimental-chat11-10· LMArena data1,446.3
90GPT 5.1· LMArena data1,445.8
91Qwen3 235B A22B Instruct 25072507· LMArena data1,445.6
92DeepSeek R10528· LMArena data1,445.5
93DeepSeek V3.1Thinking· LMArena data1,444.2
94Claude Opus 4.520251101· LMArena data1,443.4
95Claude Sonnet 4.520250929· LMArena data1,443.4
96Step 5 Preview· LMArena data1,443.3
97Grok 4.1· LMArena data1,442.5
98Claude Sonnet 5High· LMArena data1,442.3
99Qwen3.6 Plus· LMArena data1,441.6
100GPT-5.2 Chat20260210· LMArena data1,441.1

Showing 51–100 of 391 results.

Data credits: LMArena, CC BY 4.0 (licence)