Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Accuracy Evaluation on TruthfulQA
Loading...
55.67
Accuracy
GANPO
19.9252
29.2051
38.485
47.7649
Jan 29, 2026
Jan 30, 2026
Jan 31, 2026
Feb 1, 2026
Feb 2, 2026
Feb 3, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
GANPO
Backbone Model=Gemma2-...
2026.01
55.67
DPO
Backbone Model=Gemma2-...
2026.01
55.28
Base
Backbone Model=Gemma2-...
2026.01
53.11
ReMiT
Model Family=SmolLM3-3...
2026.02
31.95
Pre-Trained
Model Family=SmolLM3-3...
2026.02
30.23
Vanilla NTP
Model Family=SmolLM3-3...
2026.02
29.74
MiniPLM
Model Family=SmolLM3-3...
2026.02
29.13
RHO-1
Model Family=SmolLM3-3...
2026.02
28.52
Pre-Trained
Model Family=Youtu-LLM...
2026.02
27.54
ReMiT
Model Family=Youtu-LLM...
2026.02
27.42
RHO-1
Model Family=Youtu-LLM...
2026.02
26.68
Vanilla NTP
Model Family=Youtu-LLM...
2026.02
26.56
MiniPLM
Model Family=Youtu-LLM...
2026.02
26.56
ReMiT
Model Family=OLMo-1B,...
2026.02
25.58
RHO-1
Model Family=OLMo-1B,...
2026.02
23.38
MiniPLM
Model Family=OLMo-1B,...
2026.02
23.13
Vanilla NTP
Model Family=OLMo-1B,...
2026.02
22.4
Pre-Trained
Model Family=OLMo-1B,...
2026.02
21.3
Feedback
Search any
task
Search any
task