Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Memory Management on LOCOMO
Loading...
52
Overall QA F1
adaptive context compression framework
51.584
51.692
51.8
51.908
Mar 31, 2026
Overall QA F1
Retrieval F1
Recall@k
Baseline QA F1 (No Retrieval)
Average Sessions
Average Turns
Token Reduction
Latency Reduction (%)
Updated 18d ago
Evaluation Results
Method
Method
Links
Overall QA F1
Retrieval F1
Recall@k
Baseline QA F1 (No Retrieval)
Average Sessions
Average Turns
Token Reduction
Latency Reduction (%)
adaptive context compression framework
2026.03
52
41.5
77.5
-
-
-
25
10
LOCOMO method
Average tokens per con...
2026.03
51.6
41
76.7
22.4
27.2
588.2
-
-
Feedback
Search any
task
Search any
task