Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Retrieval on LITM
Loading...
100
Accuracy
Vanilla
95
97.5
100
102.5
Nov 3, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Vanilla
Backbone=Llama 3.3 70B...
2025.11
100
kvtc 8x
Backbone=Llama 3.3 70B...
2025.11
100
kvtc 10x
Backbone=Llama 3.3 70B...
2025.11
100
kvtc 16x
Backbone=Llama 3.3 70B...
2025.11
100
kvtc 20x
Backbone=Llama 3.3 70B...
2025.11
100
Feedback
Search any
task
Search any
task
