Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-Context Summarization on GovReport (test)
Loading...
16.11
ROUGE-1
FlashMem
13.51
14.185
14.86
15.535
Jan 9, 2026
ROUGE-1
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE-1
FlashMem
Model Backbone=Qwen 2....
2026.01
16.11
FlashMem
Model Backbone=Qwen 3...
2026.01
15.52
CoT-SC
Model Backbone=Qwen 2....
2026.01
14.41
MemGen
Model Backbone=Qwen 3...
2026.01
14.31
SnapKV
Model Backbone=Qwen 2....
2026.01
14.22
MemGen
Model Backbone=Qwen 2....
2026.01
13.97
CoT-SC
Model Backbone=Qwen 3...
2026.01
13.87
SnapKV
Model Backbone=Qwen 3...
2026.01
13.74
Vanilla
Model Backbone=Qwen 3...
2026.01
13.65
Vanilla
Model Backbone=Qwen 2....
2026.01
13.61
Feedback
Search any
task
Search any
task