Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (vbal)
Loading...
0.773
vbal Score
Base
-0.11412
0.11619
0.3465
0.57681
Apr 6, 2026
vbal Score
Updated 11d ago
Evaluation Results
Method
Method
Links
vbal Score
Base
Model=Llama3.1-8B
2026.04
0.773
Base
Model=Tulu3.1-8B
2026.04
0.757
Base
Model=OLMo2-7B
2026.04
0.736
Reflect-and-rephrase
Model=OLMo2-7B
2026.04
0.083
Reflect-and-rephrase
Model=Tulu3.1-8B
2026.04
0.048
Reflect-and-rephrase
Model=Llama3.1-8B
2026.04
0.027
PROF.
Model=OLMo2-7B
2026.04
-0.015
STRUCT.
Model=OLMo2-7B
2026.04
-0.017
PROF.
Model=Tulu3.1-8B
2026.04
-0.023
STRUCT.
Model=Tulu3.1-8B
2026.04
-0.03
PROF.
Model=Llama3.1-8B
2026.04
-0.04
STRUCT.
Model=Llama3.1-8B
2026.04
-0.047
SIMPL.
Model=OLMo2-7B
2026.04
-0.058
SIMPL.
Model=Tulu3.1-8B
2026.04
-0.059
SIMPL.
Model=Llama3.1-8B
2026.04
-0.08
Feedback
Search any
task
Search any
task