우리들의 비전

LiveBench 데이터 분석

이 벤치마크는?

LiveBench 데이터 분석 카테고리 점수 (0~100). 표·그래프 해석, 통계 추론, 데이터 기반 결론 도출 능력을 평가합니다.

출처: LiveBench
순위모델
#1

OpenAI

GPT-5.5

81.1
#2

OpenAI

GPT-5.4

79.3
#3

Google

Gemini 3.1 Pro

78.5
#4

Anthropic

Claude Opus 4.7

75.6
#5

Anthropic

Claude Sonnet 4.6

74.6
#6

Alibaba

Qwen3.6 Plus

69.9
#7

Anthropic

Claude Opus 4.6

69.9
#8

Z.ai

GLM-5

67.9
#9

Moonshot AI

Kimi K2.6

65.1
#10

Z.ai

GLM-5.1

63.2
#11

Grok

Grok 4.20 (Reasoning)

62.9
#12

Moonshot AI

Kimi K2.5

61.4
#13

Google

Gemma 4 31B

58.8
#14

OpenAI

GPT-5

57.0
#15

MiniMax

MiniMax M2.7

56.3
#16

Google

Gemini 3.1 Flash Lite

54.9
#17

Anthropic

Claude Sonnet 4

54.6
#18

Grok

Grok 4.1 Fast (Reasoning)

52.2
#19

Google

Gemini 2.5 Pro

51.6
#20

OpenAI

GPT-5 Mini

49.6
#21

MiniMax

MiniMax M2.5

49.6
#22

Xiaomi

MiMo-V2-Pro

49.2
#23

Anthropic

Claude Opus 4.1

49.0
#24

Google

Gemini 3 Flash

48.3
#25

OpenAI

GPT-5.4 Mini

47.4
#26

Google

Gemini 2.5 Flash

47.3
#27

Google

Gemini 2.5 Flash Lite

47.0
#28

Anthropic

Claude Sonnet 4.5

47.0
#29

Anthropic

Claude Haiku 4.5

45.1
#30

DeepSeek

DeepSeek V3.2

45.0
#31

OpenAI

GPT-5 Nano

44.3
#32

Anthropic

Claude Opus 4.5

44.2
#33

Grok

Grok 4.20

43.5
#34

Grok

Grok 4.1 Fast

40.6
#35

Arcee AI

Trinity Large Thinking

40.3
#36

OpenAI

GPT-5.4 Nano

39.1
#37

OpenAI

GPT OSS 120B

38.8
#38

NVIDIA

Nemotron 3 Super

21.2