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

Question Answering on HOTPOTQA Unfiltered

66.08Accuracy

Baseline

56.501658.988361.47563.9617May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
66.0873.952.95
2026.05
65.6473.482.96
2026.05
65.5673.442.96
2026.05
61.7471.511.9
2026.05
61.6671.391.89
2026.05
61.6371.411.89
2026.05
61.0869.6111.63
2026.05
61.0169.5911.62
2026.05
60.9369.5611.83
2026.05
56.9666.022.15
2026.05
56.8766.012.14
2026.05
56.8765.922.15