Back to Benchmarks
GLM-5 (Reasoning) vs Llama 3.3 Instruct 70B
GLM-5 (Reasoning)
Z AI
via Z.AI
vs
Llama 3.3 Instruct 70B
Meta
via Groq
Llama 3.3 Instruct 70B
(Groq)
wins 6 of 11
Index Scores
49.8
+35.3
Intelligence
14.5
44.2
+33.5
Coding
10.7
0.0
Math
+7.7
7.7
Benchmarks
0.0
MMLU Pro
+71.3
71.3
82.0
+32.2
GPQA
49.8
27.2
+23.2
HLE
4.0
0.0
LiveCode
+28.8
28.8
46.2
+20.2
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