Claude 4.5 Haiku (Reasoning) vs Llama 4 Scout | grube.ai

Back to Benchmarks

Claude 4.5 Haiku (Reasoning)

Anthropic

vs

Llama 4 Scout

Metavia Groq

Claude 4.5 Haiku (Reasoning) wins 8 of 11

Index Scores

37.1

+23.6

Intelligence

13.5

32.6

+25.9

Coding

6.7

83.7

+69.7

Math

14.0

Benchmarks

76.0

+0.8

MMLU Pro

75.2

67.2

+8.5

GPQA

58.7

9.7

+5.4

HLE

4.3

61.5

+31.6

LiveCode

29.9

43.3

+26.3

SciCode

17.0

0.0

MATH-500

+84.4

84.4

0.0

AIME

+28.3

28.3

Speed

66

TPS

+34

100

Shared

Winning delta

crafted by bart stefanski