Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Advanced Mathematical Reasoning on AIME 25 (Accuracy)
Loading...
19.9
AIME 25 Accuracy
NPG-Muse-8B
3.572
7.811
12.05
16.289
Aug 28, 2025
AIME 25 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
AIME 25 Accuracy
NPG-Muse-8B
Pass@k protocol=avg@64
2025.08
19.9
Qwen2.5-14B-Instruct-1M
Pass@k protocol=avg@64
2025.08
11.2
Qwen3-14B-Base
Pass@k protocol=avg@64
2025.08
10.6
Qwen3-8B-Base
Pass@k protocol=avg@64
2025.08
10.5
NPG-Muse-7B
Pass@k protocol=avg@64
2025.08
6.5
Qwen2.5-7B-Ins-1M
Pass@k protocol=avg@64
2025.08
4.2
Feedback
Search any
task
Search any
task