Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Arithmetic on arithmetic LLAMA-3.2-3B-INSTRUCT (test)
Loading...
70.2
Avg@16
RLVR
29.12
39.785
50.45
61.115
Oct 10, 2025
Avg@16
Pass@16
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@16
Pass@16
RLVR
Model=LLAMA-3.2-3B-INS...
2025.10
70.2
87.8
RLER
Model=LLAMA-3.2-3B-INS...
2025.10
63.9
75.2
RLER
Model=LLAMA-3.2-3B-INS...
2025.10
62.3
74.4
RLER
Model=LLAMA-3.2-3B-INS...
2025.10
61.9
78.6
RLER
Model=LLAMA-3.2-3B-INS...
2025.10
58.7
69.8
RLIR INTUITOR
Model=LLAMA-3.2-3B-INS...
2025.10
50.3
54.2
RLIR SC
Model=LLAMA-3.2-3B-INS...
2025.10
48.4
54.4
RLIR Freq
Model=LLAMA-3.2-3B-INS...
2025.10
47.5
56.2
RLIR Judge
Model=LLAMA-3.2-3B-INS...
2025.10
41.7
77.3
pre-RL
Model=LLAMA-3.2-3B-INS...
2025.10
30.7
80.2
Feedback
Search any
task
Search any
task