Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (vbal)
Loading...
0.778
VBAL Score
Base
-0.0488
0.16585
0.3805
0.59515
Apr 6, 2026
VBAL Score
Updated 11d ago
Evaluation Results
Method
Method
Links
VBAL Score
Base
Model=Tulu3.1-8B
2026.04
0.778
Base
Model=Llama3.1-8B
2026.04
0.763
Base
Model=OLMo2-7B
2026.04
0.734
Reflect-and-rephrase
Model=OLMo2-7B
2026.04
0.061
Reflect-and-rephrase
Model=Llama3.1-8B
2026.04
0.04
STRUCT.
Model=OLMo2-7B
2026.04
0.03
PROF.
Model=Llama3.1-8B
2026.04
0.028
PROF.
Model=OLMo2-7B
2026.04
0.026
Reflect-and-rephrase
Model=Tulu3.1-8B
2026.04
0.024
SIMPL.
Model=OLMo2-7B
2026.04
0.02
STRUCT.
Model=Llama3.1-8B
2026.04
0.012
SIMPL.
Model=Llama3.1-8B
2026.04
0.002
PROF.
Model=Tulu3.1-8B
2026.04
-0.003
STRUCT.
Model=Tulu3.1-8B
2026.04
-0.01
SIMPL.
Model=Tulu3.1-8B
2026.04
-0.017
Feedback
Search any
task
Search any
task