Back to Benchmarks

GPT-4.1 vs Llama 3.3 Instruct 70B

GPT-4.1

OpenAI

vs

Llama 3.3 Instruct 70B

Metavia Groq

GPT-4.1 wins 10 of 11

Index Scores

26.3
+11.8
Intelligence
14.5
21.8
+11.1
Coding
10.7
34.7
+27.0
Math
7.7

Benchmarks

80.6
+9.3
MMLU Pro
71.3
66.6
+16.8
GPQA
49.8
4.6
+0.6
HLE
4.0
45.7
+16.9
LiveCode
28.8
38.1
+12.1
SciCode
26.0
91.3
+14.0
MATH-500
77.3
43.7
+13.7
AIME
30.0

Speed

44
TPS
+100
144
Shared
Winning delta

crafted by bart stefanski