Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Contract Understanding on ContractNLI
Loading...
4.04
Expected Calibration Error (ECE)
CaliDist(As.)
3.01
9.9625
16.915
23.8675
Jun 4, 2026
Expected Calibration Error (ECE)
Brier Score (BS)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Expected Calibration Error (ECE)
Brier Score (BS)
CaliDist(As.)
LLM=Llama-3.1, Distrac...
2026.06
4.04
22.59
CaliDist verbalized (As.)
LLM=Llama-3.1, Distrac...
2026.06
4.63
23.25
FSD
LLM=Llama-3.1, Distrac...
2026.06
19.16
26.1
Consistency
LLM=Llama-3.1, Distrac...
2026.06
23.84
27.67
Entropy
LLM=Llama-3.1, Distrac...
2026.06
28.7
30.58
Vanilla Verbal
LLM=Llama-3.1, Distrac...
2026.06
29.79
30.98
Feedback
Search any
task
Search any
task