Back to Benchmarks

GPT-5.4 (xhigh) vs Llama 3.3 Instruct 70B

GPT-5.4 (xhigh)

OpenAI

vs

Llama 3.3 Instruct 70B

Metavia Groq

Llama 3.3 Instruct 70B(Groq) wins 6 of 11

Index Scores

57.2
+42.7
Intelligence
14.5
57.3
+46.6
Coding
10.7
0.0
Math
+7.7
7.7

Benchmarks

0.0
MMLU Pro
+71.3
71.3
92.0
+42.2
GPQA
49.8
41.6
+37.6
HLE
4.0
0.0
LiveCode
+28.8
28.8
56.6
+30.6
SciCode
26.0
0.0
MATH-500
+77.3
77.3
0.0
AIME
+30.0
30.0

Speed

32
TPS
+112
144
Shared
Winning delta

crafted by bart stefanski