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

Multi-hop Question Answering on HotPotQA (Acc, TTFT, Delay (s))

60.3Accuracy

StreamingThinker

53.43655.2185758.782Oct 20, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
60.324.326.5
2025.10
59.824.3214.45
2025.10
58.124.323.92
2025.10
57.624.3212.02
2025.10
57.51,485.54720.37
2025.10
54.424.320.69
2025.10
53.724.328.33