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
101GPT 5.4· LMArena data1,440.4
102DeepSeek V3.2· LMArena data1,439.8
103Qwen 3.8 27B· LMArena data1,438.6
104DeepSeek-V4-Flash PreviewHigh· LMArena data1,437.9
105Gemini 3.5 Flash Lite· LMArena data1,437.5
106Grok 4.5· LMArena data1,437
107MiMo V2 Pro· LMArena data1,435.3
108Grok 40709· LMArena data1,435.1
109MiniMax M3· LMArena data1,432.1
110DeepSeek V3.1· LMArena data1,432
111MiMo V2.5· LMArena data1,431.8
112Qwen3 VL 235B· LMArena data1,431.6
113GPT-6.1 SolMax· LMArena data1,431.4
114nova-experimental-chat26-02-10· LMArena data1,431.4
115MiMo V2 Omni· LMArena data1,431.3
116ERNIE-5.0-Preview1022· LMArena data1,430.7
117Claude Opus 4.5High, 32K, 20251101· LMArena data1,430.3
118GPT-5.6 TerraxHigh· LMArena data1,429.8
119Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,429.5
120GPT-5.6 SolxHigh· LMArena data1,428.9
121LongCat-Flash-Chat Exp2602· LMArena data1,428.1
122Gemini 3.1 Flash Lite· LMArena data1,427.9
123Gemini 2.5 Flash· LMArena data1,427.6
124Gemma 4 26B A4B· LMArena data1,427.1
125DeepSeek V3.2 Exp· LMArena data1,425.9
126GPT 5.2· LMArena data1,424.9
127Gemini 2.5 Flash Preview09-2025· LMArena data1,424.8
128GPT-6 AstraMax· LMArena data1,423.8
129Qwen3.5 122B-A10B· LMArena data1,423.7
130Grok 4.6High· LMArena data1,423.6
131Qwen3.5 27B· LMArena data1,423.6
132Qwen3.5 35B A3B· LMArena data1,421.6
133DeepSeek V3.2Thinking· LMArena data1,421
134GPT 5.2High· LMArena data1,420.7
135Hunyuan TurboS20250416· LMArena data1,420.2
136Kimi K3.1 ProMax· LMArena data1,418.4
137Kimi K2 Thinking· LMArena data1,416.7
138Grok 4 FastReasoning· LMArena data1,416.3
139Grok 4 FastNon-Reasoning· LMArena data1,415.6
140Kimi K2.5Instant· LMArena data1,415.2
141Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,415
142Qwen3 VL 235Bthinking· LMArena data1,414.9
143Inkling Small· LMArena data1,413.6
144GPT 5High· LMArena data1,413.4
145MiMo V2 FlashNon-Thinking· LMArena data1,413.1
146Claude Opus 4.120250805· LMArena data1,412.4
147GPT-5 Chat· LMArena data1,412.4
148GPT-5.5 Instant· LMArena data1,412.1
149Grok 4.1 FastReasoning· LMArena data1,412.1
150GPT-4.5 Preview2025-02-27· LMArena data1,410.9

Showing 101–150 of 391 results.

Data credits: LMArena, CC BY 4.0 (licence)