List your company

Question Answering on HotpotQA distractor setting

67.8F1 ScoreHAGE
6.75222.60138.4554.299May 11, 2026

Evaluation results

MethodLinks
HAGELLM Backbone=GPT-4o-mini2026.0567.882.4
MAGMALLM Backbone=GPT-4o-mini2026.056480.7
MemSkillLLM Backbone=GPT-4o-mini2026.0557.977.9
MemoryOSLLM Backbone=GPT-4o-mini2026.0547.759.2
A-MEMLLM Backbone=GPT-4o-mini2026.0543.354.7
HAGELLM Backbone=Qwen2.5-3B2026.0542.952.7
MemoryOSLLM Backbone=Qwen2.5-3B2026.053545.9
MAGMALLM Backbone=Qwen2.5-3B2026.0533.742.4
A-MEMLLM Backbone=Qwen2.5-3B2026.0518.641.6
MemSkillLLM Backbone=Qwen2.5-3B2026.0517.924.7
NemoriLLM Backbone=GPT-4o-mini2026.0513.162.4
NemoriLLM Backbone=Qwen2.5-3B2026.059.133.2