Back to Benchmarks

GPT-4.1 vs Llama 4 Scout

GPT-4.1

OpenAI

vs

Llama 4 Scout

Metavia Groq

GPT-4.1 wins 10 of 11

Index Scores

26.3
+12.8
Intelligence
13.5
21.8
+15.1
Coding
6.7
34.7
+20.7
Math
14.0

Benchmarks

80.6
+5.4
MMLU Pro
75.2
66.6
+7.9
GPQA
58.7
4.6
+0.3
HLE
4.3
45.7
+15.8
LiveCode
29.9
38.1
+21.1
SciCode
17.0
91.3
+6.9
MATH-500
84.4
43.7
+15.4
AIME
28.3

Speed

44
TPS
+56
100
Shared
Winning delta

crafted by bart stefanski