Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Expected Calibration Error on 2Wiki
Loading...
17.43
ECE
CDKC
15.7528
27.0739
38.395
49.7161
Feb 13, 2026
ECE
Updated 4d ago
Evaluation Results
Method
Method
Links
ECE
CDKC
Backbone=Qwen2.5-7B-In...
2026.02
17.43
CDKC
Backbone=Qwen2.5-7B-In...
2026.02
20.44
GRPO
Backbone=Qwen2.5-7B-In...
2026.02
20.94
BARREL
Backbone=Qwen2.5-7B-In...
2026.02
37.74
Know What
Backbone=Qwen2.5-7B-In...
2026.02
43.79
CRew-DPO
Backbone=Qwen2.5-7B-In...
2026.02
47.56
LLKD-SFT
Backbone=Qwen2.5-7B-In...
2026.02
48.11
CGKE
Backbone=Qwen2.5-7B-In...
2026.02
49.01
Vanilla SFT
Backbone=Qwen2.5-7B-In...
2026.02
57.87
Vanilla LLM
Backbone=Qwen2.5-7B-In...
2026.02
59.36
Feedback
Search any
task
Search any
task