Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination prediction on Mintaka (original)
Loading...
79.41
AUROC
Conf + Probe (SCAO)
64.2988
68.2219
72.145
76.0681
Sep 18, 2025
AUROC
A(ϕ(sM))
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
A(ϕ(sM))
Conf + Probe (SCAO)
Model Size=8B
2025.09
79.41
10.86
Conf + Probe
Model Size=8B
2025.09
79.1
10.55
Conf + Probe
Model Size=70B
2025.09
78.93
13.18
Conf + Probe (SCAO)
Model Size=70B
2025.09
78.86
13.11
Probe_dnn
Model Size=8B
2025.09
77.09
8.54
Probe_dnn
Model Size=70B
2025.09
76.43
10.68
Conf (SCAO)
Model Size=70B
2025.09
73.64
-
Conf (SCAO)
Model Size=8B
2025.09
72.13
-
Conf
Model Size=70B
2025.09
69.41
-
Conf
Model Size=8B
2025.09
64.88
-
Feedback
Search any
task
Search any
task