Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (Pass@1 Avg@32)
Loading...
89.9
Pass@1 (Avg@32)
Fold-RL
78.772
81.661
84.55
87.439
Feb 3, 2026
Pass@1 (Avg@32)
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 (Avg@32)
Fold-RL
Model Backbone=Qwen2.5...
2026.02
89.9
Mix-RL
Model Backbone=Qwen2.5...
2026.02
89.6
Unfold-RL
Model Backbone=Qwen2.5...
2026.02
89.2
Fold-RL
Model Backbone=Qwen3-4...
2026.02
89.1
Unfold-RL
Model Backbone=Qwen3-4...
2026.02
88.9
Mix-RL
Model Backbone=Qwen3-4...
2026.02
88.6
Unfold-RL
Model Backbone=Qwen2.5...
2026.02
87.3
Cold-Start
Model Backbone=Qwen2.5...
2026.02
86.2
Unfold-RL
Model Backbone=Qwen3-4...
2026.02
85.6
Zero-RL
Model Backbone=Qwen3-4...
2026.02
85.5
Cold-Start
Model Backbone=Qwen3-4...
2026.02
84.7
Cold-Start
Model Backbone=Qwen2.5...
2026.02
82.3
Zero-RL
Model Backbone=Qwen2.5...
2026.02
82.2
Cold-Start
Model Backbone=Qwen3-4...
2026.02
79.2
Feedback
Search any
task
Search any
task