Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (FRS, pass@1 accuracy)
Loading...
98.9
FRS
DS-R1-7B
38.892
54.471
70.05
85.629
Apr 13, 2026
FRS
Pass@1 Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
FRS
Pass@1 Accuracy
DS-R1-7B
Filtering rate=10%, De...
2026.04
98.9
-
DS-R1-1.5B
Filtering rate=10%, De...
2026.04
95.1
-
Phi-4
Filtering rate=10%, De...
2026.04
91.5
-
Qwen3-4B
Filtering rate=10%, De...
2026.04
90.9
-
Qwen2.5-Math
Filtering rate=10%, De...
2026.04
90.8
-
Phi-4-Reas.
Filtering rate=10%, De...
2026.04
84.5
-
LLaMA-3.1-8B
Filtering rate=10%, De...
2026.04
79.9
-
Qwen2.5-7B
Filtering rate=10%, De...
2026.04
65.6
-
Gemma-7B
Filtering rate=10%, De...
2026.04
41.2
-
Feedback
Search any
task
Search any
task