Back to Benchmarks

Claude Opus 4.6 (Adaptive Reasoning, Max Effort) vs Llama 3.3 Instruct 70B

Claude Opus 4.6 (Adaptive Reasoning, Max Effort)

Anthropic

vs

Llama 3.3 Instruct 70B

Metavia Groq

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

Index Scores

53.0
+38.5
Intelligence
14.5
48.1
+37.4
Coding
10.7
0.0
Math
+7.7
7.7

Benchmarks

0.0
MMLU Pro
+71.3
71.3
89.6
+39.8
GPQA
49.8
36.7
+32.7
HLE
4.0
0.0
LiveCode
+28.8
28.8
51.9
+25.9
SciCode
26.0
0.0
MATH-500
+77.3
77.3
0.0
AIME
+30.0
30.0

Speed

36
TPS
+108
144
Shared
Winning delta

crafted by bart stefanski