Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Closed-book Question Answering on SimpleQA (train)

18.8Accuracy

SFT

-0.2324.7099.6514.591May 16, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
18.8
2026.05
16.8
2026.05
10.5
2026.05
10.4
2026.05
9.3
2026.05
9
2026.05
8.5
2026.05
8.5
2026.05
8.3
2026.05
7.8
2026.05
7.5
2026.05
7.1
2026.05
6.8
2026.05
6.3
2026.05
6
2026.05
3.9
2026.05
3.4
2026.05
3.4
2026.05
2.9
2026.05
2.5
2026.05
0.5