Claude 4.5 Haiku (Reasoning) vs GPT-4o (Aug '24) | grube.ai

Back to Benchmarks

Claude 4.5 Haiku (Reasoning)

Anthropic

vs

GPT-4o (Aug '24)

OpenAI

Claude 4.5 Haiku (Reasoning) wins 9 of 11

Index Scores

37.1

+18.5

Intelligence

18.6

32.6

+16.0

Coding

16.6

83.7

+83.7

Math

0.0

Benchmarks

76.0

+76.0

MMLU Pro

0.0

67.2

+15.1

GPQA

52.1

9.7

+6.8

HLE

2.9

61.5

+29.8

LiveCode

31.7

43.3

+10.2

SciCode

33.1

0.0

MATH-500

+79.5

79.5

0.0

AIME

+11.7

11.7

Speed

66

+52

TPS

14

Shared

Winning delta

crafted by bart stefanski