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

Recall-Intensive Evaluation on Recall-Intensive Tasks

69.48FDA Accuracy

GLA-H

3.835220.877637.9254.9624Oct 8, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.10
69.4846.7757.0527.1540.2821.4743.7
2025.10
68.351.8358.5926.4242.3622.4244.99
2025.10
68.352.4859.627.1845.5825.4446.43
2025.10
66.7649.0259.0629.341.1524.0144.88
2025.10
65.350.8955.9228.5441.9922.4644.18
2025.10
62.1345.3643.7820.6231.1718.7836.97
2025.10
58.8639.3644.1417.0131.3718.2134.83
2025.10
55.6839.5545.518.3427.9817.6334.11
2025.10
53.8648.5546.5620.5638.623.4838.6
2025.10
52.3238.839.415.2429.8317.9232.25
2025.10
46.1425.8745.9718.9433.2220.0331.7
2025.10
44.3232.4358.4724.4942.5921.5637.31
2025.10
30.2527.6558.2323.2234.0620.3632.3
2025.10
27.6130.9356.2822.2735.0419.4531.93
2025.10
23.2532.857.0522.9635.5720.6532.05
2025.10
20.5323.2444.9114.9828.5516.4824.78
2025.10
11.2616.7843.912.7727.8517.6821.71
2025.10
6.3616.8742.1814.621.916.7219.77