Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (test) (pass@k)
Loading...
9.61
Pass Rate @8
TS-DFM
4.6492
5.9371
7.225
8.5129
May 8, 2026
Pass Rate @8
Pass Rate @16
Pass Rate @32
Updated 23d ago
Evaluation Results
Method
Method
Links
Pass Rate @8
Pass Rate @16
Pass Rate @32
TS-DFM
Steps=4, Scale=1.3B
2026.05
9.61
15.43
25.47
FS-DFM
Steps=4, Scale=1.3B
2026.05
9.41
15.29
23.05
TS-DFM
Steps=8, Scale=1.3B
2026.05
9.17
15.79
25.19
Teacher
Steps=256, Scale=1.3B,...
2026.05
9.12
16.39
27.52
FS-DFM
Steps=8, Scale=1.3B
2026.05
8.99
15.48
24.94
Teacher
Steps=32, Scale=1.3B
2026.05
7.74
15.69
22.16
Teacher
Steps=8, Scale=1.3B
2026.05
5.68
11.69
20.92
Teacher
Steps=4, Scale=1.3B
2026.05
4.84
10.3
18.49
Feedback
Search any
task
Search any
task