Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (100-question subset, test)
Loading...
82
Accuracy
SnapKV-D
31.04
44.27
57.5
70.73
Dec 12, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
SnapKV-D
Base Model=R1-Distill-...
2025.12
82
SeerAttention
Base Model=R1-Distill-...
2025.12
82
SnapKV-D
Base Model=R1-Distill-...
2025.12
81
SnapKV-D
Base Model=R1-Distill-...
2025.12
80
SeerAttention
Base Model=R1-Distill-...
2025.12
80
SnapKV-D
Base Model=R1-Distill-...
2025.12
78
SeerAttention
Base Model=R1-Distill-...
2025.12
70
SeerAttention
Base Model=R1-Distill-...
2025.12
66
H2O
Base Model=R1-Distill-...
2025.12
64
H2O
Base Model=R1-Distill-...
2025.12
62
H2O
Base Model=R1-Distill-...
2025.12
56
H2O
Base Model=R1-Distill-...
2025.12
33
Feedback
Search any
task
Search any
task