Claude 4.5 Haiku (Reasoning) vs Gemini 2.0 Flash-Lite (Feb '25) | grube.ai

Back to Benchmarks

Claude 4.5 Haiku (Reasoning)

Anthropic

vs

Gemini 2.0 Flash-Lite (Feb '25)

Google

Claude 4.5 Haiku (Reasoning) wins 9 of 11

Index Scores

37.1

+22.4

Intelligence

14.7

32.6

+32.6

Coding

0.0

83.7

+83.7

Math

0.0

Benchmarks

76.0

+3.6

MMLU Pro

72.4

67.2

+13.7

GPQA

53.5

9.7

+6.1

HLE

3.6

61.5

+43.0

LiveCode

18.5

43.3

+18.3

SciCode

25.0

0.0

MATH-500

+87.3

87.3

0.0

AIME

+27.7

27.7

Speed

66

+44

TPS

22

Shared

Winning delta

crafted by bart stefanski