Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Evaluation on MCEval HaluEval 8K (test)
Loading...
82.2
Accuracy
Act
50.792
58.946
67.1
75.254
Dec 24, 2024
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Act
Model=Llama3.2-3B
2024.12
82.2
Act
Model=Qwen2.5-7B
2024.12
82.1
Act
Model=Llama3.1-8B
2024.12
80.7
Magn-Probe
Model=Llama3.1-8B
2024.12
79.8
Act
Model=Llama2-7B
2024.12
78.8
Magn-Probe
Model=Llama2-7B
2024.12
78.3
Magn-Probe
Model=Llama3.2-3B
2024.12
78
Magn-Probe
Model=Qwen2.5-7B
2024.12
77.3
Magn-Probe
Model=Llama2-70B
2024.12
76.3
LM-Prob
Model=Llama2-70B
2024.12
75.4
LM-Prob
Model=Llama3.1-8B
2024.12
67.4
LM-Prob
Model=Llama3.2-3B
2024.12
65
LM-Prob
Model=Qwen2.5-7B
2024.12
63.7
LM-Prob
Model=Llama2-7B
2024.12
52
Feedback
Search any
task
Search any
task