Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on Minerva (Pass@1)
Loading...
33.32
Pass@1
VHG (Soft)
23.3568
25.9434
28.53
31.1166
May 7, 2026
Pass@1
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pass@1
VHG (Soft)
2026.05
33.32
Vanilla-GRPO
training_variant=w. SF...
2026.05
32.63
Vanilla-GRPO
2026.05
31.92
R-Zero
Iteration=2
2026.05
28.52
R-Zero
Iteration=3
2026.05
28.12
Qwen3-4B-Base
2026.05
27.78
R-Zero
Iteration=1
2026.05
23.74
Feedback
Search any
task
Search any
task