Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-class Calibration on R52 (test)
Loading...
1.7
NLL
NA-FIR
1.448
3.149
4.85
6.551
Dec 9, 2025
NLL
CONF-ECE
BS
CW-ECE
TECE
Updated 4d ago
Evaluation Results
Method
Method
Links
NLL
CONF-ECE
BS
CW-ECE
TECE
NA-FIR
Type=Average Ranking
2025.12
1.7
2.6
2.4
3.8
6.1
TS
Type=Average Ranking
2025.12
2.1
4.8
3.9
4.7
5.1
FIR
Type=Average Ranking
2025.12
3.2
3.6
2.9
2.7
5.3
UNCALIBRATED
Type=Average Ranking
2025.12
4.1
6.9
5.5
5.3
6.4
SCIR
Type=Average Ranking
2025.12
5.1
2.9
4.9
5
2.7
VS
Type=Average Ranking
2025.12
5.1
3.8
3.9
2.8
3.6
MS
Type=Average Ranking
2025.12
6.7
5.1
6.8
7.2
3.2
IR OVR
Type=Average Ranking
2025.12
8
6.3
5.7
4.5
3.6
Feedback
Search any
task
Search any
task