List your company

Long-Context Summarization on GovReport (test)

16.11ROUGE-1FlashMem
13.5114.18514.8615.535Jan 9, 2026

Evaluation results

MethodLinks
FlashMemModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=FlashMem2026.0116.11
FlashMemModel Backbone=Qwen 3 4B Instruct, Inference Strategy=FlashMem2026.0115.52
CoT-SCModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=CoT-SC2026.0114.41
MemGenModel Backbone=Qwen 3 4B Instruct, Inference Strategy=MemGen2026.0114.31
SnapKVModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=SnapKV2026.0114.22
MemGenModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=MemGen2026.0113.97
CoT-SCModel Backbone=Qwen 3 4B Instruct, Inference Strategy=CoT-SC2026.0113.87
SnapKVModel Backbone=Qwen 3 4B Instruct, Inference Strategy=SnapKV2026.0113.74
VanillaModel Backbone=Qwen 3 4B Instruct, Inference Strategy=Vanilla2026.0113.65
VanillaModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=Vanilla2026.0113.61