Back to Benchmarks

Gemma 4 31B (Reasoning) vs Llama 3.3 Instruct 70B

Gemma 4 31B (Reasoning)

Googlevia DeepInfra

vs

Llama 3.3 Instruct 70B

Metavia Groq

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

Index Scores

39.2
+24.7
Intelligence
14.5
38.7
+28.0
Coding
10.7
0.0
Math
+7.7
7.7

Benchmarks

0.0
MMLU Pro
+71.3
71.3
85.7
+35.9
GPQA
49.8
22.7
+18.7
HLE
4.0
0.0
LiveCode
+28.8
28.8
43.4
+17.4
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