Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on AIME 2024 (Pass@1 %)
Loading...
13.96
Pass@1 Accuracy
Vanilla-GRPO
7.0232
8.8241
10.625
12.4259
May 7, 2026
Pass@1 Accuracy
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Vanilla-GRPO
2026.05
13.96
VHG (Soft)
2026.05
13.12
Vanilla-GRPO
training_variant=w. SF...
2026.05
11.04
R-Zero
Iteration=3
2026.05
10.83
R-Zero
Iteration=1
2026.05
10.62
R-Zero
Iteration=2
2026.05
10
Qwen3-4B-Base
2026.05
7.29
Feedback
Search any
task
Search any
task