Claude 4.5 Haiku (Reasoning) vs GPT-4o mini | grube.ai

Back to Benchmarks

Claude 4.5 Haiku (Reasoning)

Anthropic

vs

GPT-4o mini

OpenAI

Claude 4.5 Haiku (Reasoning) wins 9 of 11

Index Scores

37.1

+24.5

Intelligence

12.6

32.6

+32.6

Coding

0.0

83.7

+69.0

Math

14.7

Benchmarks

76.0

+11.2

MMLU Pro

64.8

67.2

+24.6

GPQA

42.6

9.7

+5.7

HLE

4.0

61.5

+38.1

LiveCode

23.4

43.3

+20.4

SciCode

22.9

0.0

MATH-500

+78.9

78.9

0.0

AIME

+11.7

11.7

Speed

66

+36

TPS

30

Shared

Winning delta

crafted by bart stefanski