Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math Word Problem Solving on GSM+ v1 (test)
Loading...
65.7
Accuracy
Full-FT
10.372
24.736
39.1
53.464
Feb 12, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Full-FT
Backbone=Qwen3-8B-Base...
2026.02
65.7
PrefillShare
Backbone=Qwen3-8B-Base...
2026.02
64.5
Full-FT
Backbone=LLaMA3.1-8B,...
2026.02
49.8
PrefillShare
Backbone=LLaMA3.1-8B,...
2026.02
49.3
LLaMA3.1-8B
KV Sharing=Inherent
2026.02
18
Qwen3-8B-Base
KV Sharing=Inherent
2026.02
12.5
Feedback
Search any
task
Search any
task