Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (τ, Tokens/s, Speedup)
Loading...
48.31
Tokens/s
SAGE
19.918
27.289
34.66
42.031
Jan 31, 2026
Tokens/s
Avg Accepted Length (τ)
Speedup
Updated 4d ago
Evaluation Results
Method
Method
Links
Tokens/s
Avg Accepted Length (τ)
Speedup
SAGE
Setup=Llama3 8B-1B
2026.01
48.31
4.05
2.3
Native-SD
Setup=Llama3 8B-1B
2026.01
44.59
3.12
2.12
Vanilla
Setup=Llama3 8B-1B
2026.01
21.01
-
-
Feedback
Search any
task
Search any
task
