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

Long-context Question Answering on LoCoMo (Rubric Judge)

67.3Rubric Judge Accuracy

Baseline

56.06858.98461.964.816May 7, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.05
67.3
2026.05
66.6
2026.05
65.9
2026.05
65.7
2026.05
65.4
2026.05
65.4
2026.05
65.1
2026.05
65
2026.05
63.6
2026.05
63
2026.05
62.5
2026.05
59.4
2026.05
57.2
2026.05
57.2
2026.05
56.5