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
201Qwen 3 235B A22B· LMArena data1,363.4
202Mercury 2· LMArena data1,363.3
203Step3· LMArena data1,362.6
204GPT-6 SolMax· LMArena data1,362.5
205o4 Mini2025-04-16· LMArena data1,361.5
206Ling Flash 2.0· LMArena data1,359.2
207MiniMax M2.5· LMArena data1,358.3
208Claude Opus 4Thinking 16K, 20250514· LMArena data1,355.6
209MiniMax M1· LMArena data1,355
210o12024-12-17· LMArena data1,355
211Step-2 16K Exp202412· LMArena data1,354.9
212GPT-6 LunaMax· LMArena data1,352.7
213Qwen Plus0125· LMArena data1,350.1
214Step-1o Turbo202506· LMArena data1,349.6
215Nemotron 3 Nano 30B A3BBF16· LMArena data1,349.4
216Trinity Large Thinking· LMArena data1,349.1
217GLM 4.5V· LMArena data1,347.6
218Qwen3 Coder· LMArena data1,346.6
219Mistral Small 3.22506· LMArena data1,346.2
220Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,345.8
221DeepSeek V3· LMArena data1,345.4
222GLM 4.7 Flash· LMArena data1,344.4
223Trinity Large Preview· LMArena data1,344.1
224Gemma 3 4B IT· LMArena data1,342
225Hunyuan Large2025-02-10· LMArena data1,340.2
226QwQ 32B· LMArena data1,340.1
227GPT-5 nanoHigh· LMArena data1,335
228Command A03-2025· LMArena data1,334.4
229Gemma 3 12B IT· LMArena data1,334.4
230Ring Flash 2.0· LMArena data1,333.1
231o3 MiniHigh· LMArena data1,330.4
232Claude Sonnet 420250514· LMArena data1,329.8
233Granite 4.2 8B· LMArena data1,329.5
234Granite 4.2 30B· LMArena data1,329
235Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,326.5
236GPT-4.1 mini2025-04-14· LMArena data1,324.9
237INTELLECT-3· LMArena data1,322.7
238Gemma 3n E4B IT· LMArena data1,320.9
239Qwen3 30B A3B· LMArena data1,317.8
240Olmo 3 32B Think· LMArena data1,313.4
241GPT OSS 20b· LMArena data1,310.5
242Hunyuan Standard2025-02-10· LMArena data1,309.5
243O1 Preview· LMArena data1,307.1
244Grok 22024-08-13· LMArena data1,306.7
245Yi Lightning· LMArena data1,306.1
246Gemini 1.5 Pro002· LMArena data1,305.9
247Qwen2.5-Plus1127· LMArena data1,301.9
248Llama 3.1 Nemotron 70B Instruct· LMArena data1,301.1
249o3 Mini· LMArena data1,298.8
250Grok 2 mini2024-08-13· LMArena data1,297.9

Showing 201–250 of 391 results.

Data credits: LMArena, CC BY 4.0 (licence)