경영·금융

이 벤치마크는?

비즈니스 관련 전문가 프롬프트에서의 Arena Elo 점수입니다.

출처: Arena Intelligence
순위모델
#1

Anthropic

Claude Opus 4.6

1501
#2

Grok

Grok 4.20

1491
#3

Grok

Grok 4.20 (Reasoning)

1491
#4

OpenAI

GPT-5.4

1488
#5

OpenAI

GPT-5.4 Pro

1488
#6

Anthropic

Claude Sonnet 4.6

1484
#7

Google

Gemini 3.1 Pro

1482
#8

OpenAI

GPT-5.4 Mini

1477
#9

Google

Gemini 3 Flash

1471
#10

Anthropic

Claude Opus 4.5

1469
#11

Z.ai

GLM-5.1

1465
#12

Xiaomi

MiMo-V2-Pro

1458
#13

Anthropic

Claude Sonnet 4.5

1453
#14

Meituan

Longcat Flash Chat

1449
#15

Z.ai

GLM-5

1448
#16

Anthropic

Claude Opus 4.1

1447
#17

Baidu

ERNIE 5.0 Thinking

1447
#18

Qwen

Qwen3.5 397B A17B

1445
#19

Google

Gemma 4 31B

1443
#20

Google

Gemini 2.5 Pro

1436
#21

Moonshot AI

Kimi K2.5

1436
#22

Google

Gemini 3.1 Flash Lite

1433
#23

DeepSeek

DeepSeek V3.2

1419
#24

Grok

Grok 4.1 Fast

1417
#25

Grok

Grok 4.1 Fast (Reasoning)

1417
#26

MiniMax

MiniMax M2.7

1415
#27

MiniMax

MiniMax M2.5

1415
#28

OpenAI

GPT-5

1414
#29

Anthropic

Claude Haiku 4.5

1413
#30

Anthropic

Claude Opus 4

1412
#31

OpenAI

GPT-5.4 Nano

1409
#32

Google

Gemini 2.5 Flash

1398
#33

Arcee AI

Trinity Large Thinking

1385
#34

Anthropic

Claude Sonnet 4

1385
#35

OpenAI

GPT-5 Mini

1380
#36

Google

Gemini 2.5 Flash Lite

1378
#37

OpenAI

GPT OSS 120B

1349
#38

Amazon

Nova 2 Lite

1349
#39

OpenAI

GPT-5 Nano

1335
#40

Meta AI

Llama 4 Maverick

1320
#41

Meta AI

Llama 4 Scout

1319
#42

OpenAI

GPT-4.1

1282