Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Expected Calibration Error on TriQA
Loading...
8.58
Expected Calibration Error
CDKC
7.4304
15.1902
22.95
30.7098
Feb 13, 2026
Expected Calibration Error
Updated 1mo ago
Evaluation Results
Method
Method
Links
Expected Calibration Error
CDKC
Backbone=Qwen2.5-7B-In...
2026.02
8.58
GRPO
Backbone=Qwen2.5-7B-In...
2026.02
10.26
BARREL
Backbone=Qwen2.5-7B-In...
2026.02
13.78
CDKC
Backbone=Qwen2.5-7B-In...
2026.02
14.57
Know What
Backbone=Qwen2.5-7B-In...
2026.02
31.43
LLKD-SFT
Backbone=Qwen2.5-7B-In...
2026.02
34.96
CGKE
Backbone=Qwen2.5-7B-In...
2026.02
35.45
Vanilla LLM
Backbone=Qwen2.5-7B-In...
2026.02
35.71
Vanilla SFT
Backbone=Qwen2.5-7B-In...
2026.02
36.49
CRew-DPO
Backbone=Qwen2.5-7B-In...
2026.02
37.32
Feedback
Search any
task
Search any
task