GPT-4.1 mini vs Llama 3.3 Instruct 70B | grube.ai

Back to Benchmarks

GPT-4.1 mini

OpenAI

vs

Llama 3.3 Instruct 70B

Metavia Groq

GPT-4.1 mini wins 10 of 11

Index Scores

22.9

+8.4

Intelligence

14.5

18.5

+7.8

Coding

10.7

46.3

+38.6

Math

7.7

Benchmarks

78.1

+6.8

MMLU Pro

71.3

66.4

+16.6

GPQA

49.8

4.6

+0.6

HLE

4.0

48.3

+19.5

LiveCode

28.8

40.4

+14.4

SciCode

26.0

92.5

+15.2

MATH-500

77.3

43.0

+13.0

AIME

30.0

Speed

51

TPS

+93

144

Shared

Winning delta

crafted by bart stefanski