Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Needle-in-the-Haystack retrieval on PG-19 mini 32K context
Loading...
100
Accuracy
Quest
77.12
83.06
89
94.94
Aug 9, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Quest
Model=Llama-3.1-8B, Bu...
2025.08
100
Quest
Model=Llama-3.1-8B, Bu...
2025.08
100
TidalDecode
Model=Llama-3.1-8B, Bu...
2025.08
100
TidalDecode
Model=Llama-3.1-8B, Bu...
2025.08
100
TidalDecode
Model=Llama-3.1-8B, Bu...
2025.08
100
TidalDecode
Model=Llama-3.1-8B, Bu...
2025.08
100
LessIsMore
Model=Llama-3.1-8B, Bu...
2025.08
100
LessIsMore
Model=Llama-3.1-8B, Bu...
2025.08
100
LessIsMore
Model=Llama-3.1-8B, Bu...
2025.08
100
LessIsMore
Model=Llama-3.1-8B, Bu...
2025.08
100
LessIsMore
Model=Llama-3.1-8B, Bu...
2025.08
100
TidalDecode
Model=Llama-3.1-8B, Bu...
2025.08
98
Quest
Model=Llama-3.1-8B, Bu...
2025.08
92
Quest
Model=Llama-3.1-8B, Bu...
2025.08
88
Quest
Model=Llama-3.1-8B, Bu...
2025.08
78
Feedback
Search any
task
Search any
task