Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Exact Retrieval on Needle-in-a-Haystack (NIAH) 16K
Loading...
100
Average Accuracy
Baseline SFT
95
97.5
100
102.5
Apr 15, 2026
Average Accuracy
Updated 2d ago
Evaluation Results
Method
Method
Links
Average Accuracy
Baseline SFT
2026.04
100
MIN0.1
Anchor=MIN, p=0.1
2026.04
100
MIN0.2
Anchor=MIN, p=0.2
2026.04
100
MEAN0.1
Anchor=MEAN, p=0.1
2026.04
100
MEAN0.2
Anchor=MEAN, p=0.2
2026.04
100
Feedback
Search any
task
Search any
task