이벤트 정보

LiveBench 수학

이 벤치마크는?

LiveBench 수학 카테고리 점수 (0~100). 경시대회 수준 수학 문제, 증명, 수치 계산 등을 평가합니다.

출처: LiveBench
순위모델
#1

OpenAI

GPT-5.5

95.9
#2

Upstage

Solar Open 2

95.8
#3

Anthropic

Claude Fable 5

95.7
#4

OpenAI

GPT-5.6 Sol

95.5
#5

Anthropic

Claude Opus 4.8

95.3
#6

Anthropic

Claude Opus 5

95.2
#7

OpenAI

GPT-5.4

94.2
#8

Anthropic

Claude Sonnet 5

92.9
#9

Anthropic

Claude Opus 4.7

92.8
#10

Google

Gemini 3.1 Pro

91.0
#11

OpenAI

GPT-5.4 Nano

91.0
#12

xAI

Grok 4.5

90.8
#13

DeepSeek

DeepSeek V4 Pro

90.7
#14

Anthropic

Claude Opus 4.5

90.4
#15

Z.ai

GLM 5.2

89.8
#16

OpenAI

GPT-5.6 Terra

89.5
#17

Anthropic

Claude Opus 4.6

89.3
#18

Google

Gemini 3.5 Flash

88.2
#19

Meta

Muse Spark 1.1

87.1
#20

xAI

Grok 4.20 (Reasoning)

87.1
#21

Anthropic

Claude Sonnet 4.6

87.0
#22

Google

Gemini 3.6 Flash

86.4
#23

OpenAI

GPT-5.6 Luna

86.3
#24

OpenAI

GPT-5

86.2
#25

Alibaba

Qwen: Qwen3.7 Max

85.3
#26

Z.ai

GLM-5.1

84.9
#27

Moonshot AI

Kimi K2.5

84.9
#28

Moonshot AI

Kimi K3

84.4
#29

xAI

Grok 4.3

84.3
#30

Moonshot AI

Kimi K2.6

84.3
#31

xAI

Grok 4.1 Fast (Reasoning)

83.7
#32

Alibaba

Qwen3.6 Plus

83.7
#33

Z.ai

GLM-5

83.5
#34

MiniMax

MiniMax M2.7

80.5
#35

DeepSeek

DeepSeek V4 Flash

79.7
#36

Moonshot AI

Kimi K2.7 Code

79.6
#37

Alibaba

Qwen3.6 Flash

78.9
#38

OpenAI

GPT-5.4 Mini

78.5
#39

xAI

Grok Build 0.1

78.4
#40

MiniMax

MiniMax M2.5

77.4
#41

Xiaomi

MiMo V2 Pro

77.0
#42

MiniMax

MiniMax M3

77.0
#43

OpenAI

GPT-5 Mini

74.4
#44

Google

Gemma 4 31B

73.9
#45

Google

Gemini 3.5 Flash-Lite

73.7
#46

Google

Gemini 3.1 Flash Lite

73.6
#47

Anthropic

Claude Opus 4.1

73.2
#48

Anthropic

Claude Sonnet 4

70.5
#49

Z.ai

GLM 5V Turbo

70.4
#50

OpenAI

GPT OSS 120B

68.9
#51

Google

Gemini 2.5 Flash

68.8
#52

Google

Gemini 2.5 Pro

68.3
#53

Google

Gemini 3 Flash

68.1
#54

OpenAI

GPT-5 Nano

64.7
#55

DeepSeek

DeepSeek V3.2

64.0
#56

Anthropic

Claude Sonnet 4.5

62.6
#57

Google

Gemini 2.5 Flash Lite

61.0
#58

Anthropic

Claude Haiku 4.5

58.0
#59

NVIDIA

Nemotron 3 Ultra

54.5
#60

xAI

Grok 4.20

45.5
#61

Arcee AI

Trinity Large Thinking

44.9
#62

xAI

Grok 4.1 Fast

38.9
#63

NVIDIA

Nemotron 3 Super

36.4