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

Question Answering on OpenBookQA (Normalized Accuracy)

55.6Normalized Accuracy

Llama-Instruct

-5.34410.47826.342.122Dec 13, 2024Mar 3, 2025May 22, 2025Aug 10, 2025Oct 29, 2025Jan 17, 2026Apr 8, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.03
55.6
2026.03
52.6
2026.04
49
2026.04
47.4
2026.04
46.2
2026.04
45.6
2024.12
45
2024.12
44.8
2025.02
33.6
2025.02
33.2
2025.02
33
2025.02
32.8
2025.02
32.8
2026.04
32.8
2026.03
32.6
2026.03
32.6
2026.04
32.6
2025.02
32.4
2025.02
32.2
2026.03
32
2026.04
32
2026.04
31.8
2025.12
31.6
2026.03
31.6
2026.04
31.2
2025.12
30.8
2025.12
30.8
2026.04
30.6
2026.04
30.6
2025.02
30.4
2025.02
30.4
2025.02
30.2
2026.03
30.2
2025.12
30.18
2025.12
30
2025.02
30
2026.03
30
2026.04
30
2025.12
29.93
2025.12
29.8
2026.03
29.8
2026.03
29.6
2025.12
29.4
2025.12
29.22
2025.12
29.2
2026.03
29.2
2025.12
29
2026.03
29
2026.04
29
2026.03
28.6
2026.03
28.6
2025.12
28.4
2026.03
28.4
2026.03
28.2
2025.12
28
2026.03
27.6
2026.03
27.6
2026.03
27.2
2025.12
27
2025.12
27
2026.03
27
2026.03
26.8
2026.03
26.8
2025.12
26.6
2026.03
26.6
2026.04
26.6
2026.04
26.4
2026.03
26.2
2026.03
26.2
2026.03
26
2026.03
26
2026.03
26
2026.03
26
2026.04
26
2026.03
25.2
2026.03
25
2026.04
25
2026.04
25
2026.04
24.6
2026.04
24.6
2026.04
24.4
2026.03
23.2
2026.03
22.8
2026.03
22
2026.03
22
2026.03
21.8
2025.12
17.6
2025.12
14.4
2025.12
13.6
2025.12
9.9
2025.12
8.5
2026.04
0.4
2026.04
0
2026.04
-0.2
2025.12
-0.5
2026.04
-1
2026.04
-1.8
2026.04
-2.2
2026.04
-2.8
2026.04
-3
Showing 100 of 102 rows