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

Needle-in-the-Haystack retrieval on PG-19 mini 10K context

100Accuracy (Needle-in-the-Haystack)

Quest

72.9679.988794.02Aug 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
100
2025.08
99
2025.08
98
2025.08
98
2025.08
98
2025.08
94
2025.08
88
2025.08
86
2025.08
84
2025.08
74
2025.08
74