Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Accuracy on SQuAD (Hallucination Detection)
Loading...
85.34
Accuracy
Val Loss
58.7056
65.6203
72.535
79.4497
May 25, 2026
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
Val Loss
Model=LlaMA-3.2-3B, Fo...
2026.05
85.34
ID
Model=LlaMA-3.2-3B, Fo...
2026.05
84.61
FEPoID
Model=LlaMA-3.2-3B, Fo...
2026.05
84.61
Curvature
Model=LlaMA-3.2-3B, Fo...
2026.05
81.63
Val Loss
Model=LlaMA-3.2-1B, Fo...
2026.05
75.66
FEPoID
Model=LlaMA-3.2-1B, Fo...
2026.05
75.66
Curvature
Model=LlaMA-3.2-1B, Fo...
2026.05
73.4
RankME
Model=LlaMA-3.2-3B, Fo...
2026.05
73.38
ID
Model=LlaMA-3.2-1B, Fo...
2026.05
70.74
RGN
Model=LlaMA-3.2-1B, Fo...
2026.05
64.99
RGN
Model=LlaMA-3.2-3B, Fo...
2026.05
63.33
SNR
Model=LlaMA-3.2-3B, Fo...
2026.05
63.33
RankME
Model=LlaMA-3.2-1B, Fo...
2026.05
62.88
SNR
Model=LlaMA-3.2-1B, Fo...
2026.05
59.73
Feedback
Search any
task
Search any
task
