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

OpenBook Evaluation on OpenBook

53.2Accuracy

Cache-to-Cache

0.1613.9327.741.47Oct 3, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
53.20.34
2025.10
52.60.3
2025.10
47.80.43
2025.10
46.45.08
2025.10
45.60.35
2025.10
440.81
2025.10
41.20.7
2025.10
40.80.29
2025.10
39.20.27
2025.10
36.40.17
2025.10
32.60.07
2025.10
22.20.27
2025.10
2.21.98