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

Long-Memory Question Answering on LoCoMo (Accuracy Metrics)

97.5Accuracy (Single-Hop)

ByteRover

37.481653.063368.64584.2267Apr 2, 2026Apr 3, 2026Apr 4, 2026Apr 5, 2026Apr 6, 2026Apr 7, 2026Apr 9, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.04
97.593.385.997.896.1-
2026.04
96.0893.6270.8389.7292.73-
2026.04
93.28477.188.289.9-
2026.04
90.6180.8570.8385.3686.49-
2026.04
86.6884.0471.8860.7579.87-
2026.04
86.4475.8966.6778.581.62-
2026.04
86.270.895.183.889.6-
2026.04
85.1183.765.6288.3985.38-
2026.04
81.0967.4955.975.1875.8-
2026.04
79.5554.9658.3350.1667.6-
2026.04
74.16667.779.875.1-
2026.04
73.1264.6553.1281.272.01-
2026.04
70.946.977.285.175.8-
2026.04
67.1351.1572.9355.5166.88-
2026.04
67.151.272.955.566.9-
2026.04
66.3463.1250.0127.156.55-
2026.04
65.7147.1975.7158.1368.44-
2026.04
63.842.962.321.752.9-
2026.04
63.7942.9262.2921.7152.9-
2026.04
62.2347.9271.1223.4358.1-
2026.04
61.741.3576.649.3165.99-
2026.04
39.7918.8554.0549.9148.38-
2026.05
-----24
2026.05
-----33.7
2026.05
-----45.9
2026.05
-----49.6
2026.05
-----7.7
2026.05
-----31.6
2026.05
-----51.2
2026.05
-----56.6
2026.05
-----76.3