Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on TriviaQA (test) (EM and F1)
Loading...
35.6
EM
Ground Truth
20.104
24.127
28.15
32.173
Dec 1, 2025
EM
F1
Updated 4d ago
Evaluation Results
Method
Method
Links
EM
F1
Ground Truth
setting=SFT settings
2025.12
35.6
44.66
EPD-Judge Model
setting=SFT settings
2025.12
33.2
40.47
DP-Logits
setting=SFT settings
2025.12
26.9
31.5
LLM-Hamp
setting=SFT settings
2025.12
20.7
28.74
Feedback
Search any
task
Search any
task