Mathematical Reasoning on MATH500 (Pass@1 Avg@32)
89.9Pass@1 (Avg@32)Fold-RL
Evaluation Results
| Method | Links | |
|---|---|---|
| Fold-RLModel Backbone=Qwen2.5-Math-7B, Gen Mode=Fold2026.02 | 89.9 | |
| Mix-RLModel Backbone=Qwen2.5-Math-7B, Gen Mode=Fold2026.02 | 89.6 | |
| Unfold-RLModel Backbone=Qwen2.5-Math-7B, Gen Mode=Unfold2026.02 | 89.2 | |
| Fold-RLModel Backbone=Qwen3-4B-Base, Gen Mode=Fold2026.02 | 89.1 | |
| Unfold-RLModel Backbone=Qwen3-4B-Base, Gen Mode=Unfold2026.02 | 88.9 | |
| Mix-RLModel Backbone=Qwen3-4B-Base, Gen Mode=Fold2026.02 | 88.6 | |
| Unfold-RLModel Backbone=Qwen2.5-Math-7B, Gen Mode=Fold2026.02 | 87.3 | |
| Cold-StartModel Backbone=Qwen2.5-Math-7B, Gen Mode=Unfold2026.02 | 86.2 | |
| Unfold-RLModel Backbone=Qwen3-4B-Base, Gen Mode=Fold2026.02 | 85.6 | |
| Zero-RLModel Backbone=Qwen3-4B-Base, Gen Mode=Unfold2026.02 | 85.5 | |
| Cold-StartModel Backbone=Qwen3-4B-Base, Gen Mode=Unfold2026.02 | 84.7 | |
| Cold-StartModel Backbone=Qwen2.5-Math-7B, Gen Mode=Fold2026.02 | 82.3 | |
| Zero-RLModel Backbone=Qwen2.5-Math-7B, Gen Mode=Unfold2026.02 | 82.2 | |
| Cold-StartModel Backbone=Qwen3-4B-Base, Gen Mode=Fold2026.02 | 79.2 |