Claude 4.5 Haiku (Reasoning) vs GPT-4.1 | grube.ai

Back to Benchmarks

Claude 4.5 Haiku (Reasoning)

Anthropic

vs

GPT-4.1

OpenAI

Claude 4.5 Haiku (Reasoning) wins 8 of 11

Index Scores

37.1

+10.8

Intelligence

26.3

32.6

+10.8

Coding

21.8

83.7

+49.0

Math

34.7

Benchmarks

76.0

MMLU Pro

+4.6

80.6

67.2

+0.6

GPQA

66.6

9.7

+5.1

HLE

4.6

61.5

+15.8

LiveCode

45.7

43.3

+5.2

SciCode

38.1

0.0

MATH-500

+91.3

91.3

0.0

AIME

+43.7

43.7

Speed

66

+22

TPS

44

Shared

Winning delta

crafted by bart stefanski