Back to Benchmarks

Gemini 3 Flash Preview (Reasoning) vs Llama 3.3 Instruct 70B

Gemini 3 Flash Preview (Reasoning)

Google

vs

Llama 3.3 Instruct 70B

Metavia Groq

Gemini 3 Flash Preview (Reasoning) wins 8 of 11

Index Scores

46.4
+31.9
Intelligence
14.5
42.6
+31.9
Coding
10.7
97.0
+89.3
Math
7.7

Benchmarks

89.0
+17.7
MMLU Pro
71.3
89.8
+40.0
GPQA
49.8
34.7
+30.7
HLE
4.0
90.8
+62.0
LiveCode
28.8
50.6
+24.6
SciCode
26.0
0.0
MATH-500
+77.3
77.3
0.0
AIME
+30.0
30.0

Speed

68
TPS
+76
144
Shared
Winning delta

crafted by bart stefanski