Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Narrative QA Evaluation
Loading...
27.2
Score
ReFreeKV
4.8608
10.6604
16.46
22.2596
Feb 24, 2025
May 10, 2025
Jul 25, 2025
Oct 9, 2025
Dec 24, 2025
Mar 10, 2026
May 25, 2026
Score
Updated 26d ago
Evaluation Results
Method
Method
Links
Score
ReFreeKV
Backbone=Mistral-7B-In...
2025.02
27.2
Heavy Hitter Oracle (H2O)
Backbone=Llama3-8B-Ins...
2025.02
24.55
ReFreeKV
Backbone=Llama3-8B-Ins...
2025.02
23.44
ReFreeKV
Backbone=Qwen2.5-7B-In...
2025.02
20.66
MEMPR
Model=Qwen3 30B Think
2026.05
9.26
Human
Model=Human
2026.05
7.96
COMPACTOR
Model=Llama 3.3 70B
2026.05
5.72
Feedback
Search any
task
Search any
task