Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on AMC23 (Accuracy)
Loading...
97.5
Accuracy
w/o RLVR
33.332
49.991
66.65
83.309
Dec 3, 2025
Dec 13, 2025
Dec 24, 2025
Jan 4, 2026
Jan 14, 2026
Jan 25, 2026
Feb 5, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
w/o RLVR
Base model=Qwen3-30B-A...
2026.02
97.5
DVPO
Training Domain=Math D...
2025.12
87.5
Dr.GRPO
Training Domain=Math D...
2025.12
85.83
GRPO
Training Domain=Math D...
2025.12
84.17
Reinforce++
Training Domain=Math D...
2025.12
84.17
Robust Bellman
Training Domain=Math D...
2025.12
84.17
PPO
Training Domain=Math D...
2025.12
80
Base
Training Domain=Math D...
2025.12
75.83
LUSPO
Base model=Qwen2.5-7B-...
2026.02
58.3
GSPO
Base model=Qwen2.5-7B-...
2026.02
55.3
w/o RLVR
Base model=Qwen2.5-7B-...
2026.02
35.8
Feedback
Search any
task
Search any
task