의학·보건

이 벤치마크는?

의료 관련 전문가 프롬프트에서의 Arena Elo 점수입니다.

출처: Arena Intelligence
순위모델
#1

Grok

Grok 4.20

1523
#2

Grok

Grok 4.20 (Reasoning)

1523
#3

Anthropic

Claude Opus 4.6

1513
#4

Google

Gemini 3.1 Pro

1513
#5

Z.ai

GLM-5

1499
#6

Anthropic

Claude Opus 4.5

1490
#7

Google

Gemini 3 Flash

1486
#8

Xiaomi

MiMo-V2-Pro

1481
#9

Anthropic

Claude Opus 4.1

1480
#10

Baidu

ERNIE 5.0 Thinking

1479
#11

OpenAI

GPT-5.4 Mini

1475
#12

OpenAI

GPT-5.4

1474
#13

OpenAI

GPT-5.4 Pro

1474
#14

Z.ai

GLM-5.1

1471
#15

Google

Gemini 3.1 Flash Lite

1469
#16

Google

Gemini 2.5 Pro

1468
#17

Anthropic

Claude Sonnet 4.6

1468
#18

Moonshot AI

Kimi K2.5

1467
#19

Anthropic

Claude Sonnet 4.5

1465
#20

Google

Gemma 4 31B

1463
#21

Qwen

Qwen3.5 397B A17B

1461
#22

OpenAI

GPT-5

1456
#23

Grok

Grok 4.1 Fast

1447
#24

Grok

Grok 4.1 Fast (Reasoning)

1447
#25

Anthropic

Claude Opus 4

1447
#26

DeepSeek

DeepSeek V3.2

1443
#27

Meituan

Longcat Flash Chat

1443
#28

MiniMax

MiniMax M2.7

1442
#29

OpenAI

GPT-5.4 Nano

1440
#30

Google

Gemini 2.5 Flash

1424
#31

Anthropic

Claude Sonnet 4

1420
#32

Anthropic

Claude Haiku 4.5

1417
#33

Arcee AI

Trinity Large Thinking

1416
#34

MiniMax

MiniMax M2.5

1405
#35

OpenAI

GPT-5 Mini

1401
#36

Google

Gemini 2.5 Flash Lite

1400
#37

OpenAI

GPT OSS 120B

1368
#38

Amazon

Nova 2 Lite

1358
#39

OpenAI

GPT-5 Nano

1357
#40

Meta AI

Llama 4 Maverick

1348
#41

Meta AI

Llama 4 Scout

1344
#42

OpenAI

GPT-4.1

1307