Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Truthfulness Evaluation on TruthfulQA (Normalized Accuracy)
Loading...
58.76
Normalized Accuracy
IPO
43.42
47.4025
51.385
55.3675
Dec 13, 2024
Jan 8, 2025
Feb 3, 2025
Mar 1, 2025
Mar 27, 2025
Apr 22, 2025
May 18, 2025
Normalized Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Normalized Accuracy
IPO
Base model=Qwen-2 inst...
2025.05
58.76
SamPO
Base model=Qwen-2 inst...
2025.05
58.44
SGDPO
Base model=Qwen-2 inst...
2025.05
58.06
NCA
Base model=Qwen-2 inst...
2025.05
57.82
BCO
Base model=Qwen-2 inst...
2025.05
57.76
DPO
Base model=Qwen-2 inst...
2025.05
57.74
TDPO
Base model=Qwen-2 inst...
2025.05
57.63
SFT
Base model=Qwen-2 inst...
2025.05
57.34
Llama 3-8B E8T2
Shots=0-shot
2024.12
44.22
Llama 3-8B
Shots=0-shot
2024.12
44.01
Feedback
Search any
task
Search any
task