Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on HotpotQA distractor setting
Loading...
67.8
F1 Score
HAGE
6.752
22.601
38.45
54.299
May 11, 2026
F1 Score
LLM Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
F1 Score
LLM Score
HAGE
LLM Backbone=GPT-4o-mini
2026.05
67.8
82.4
MAGMA
LLM Backbone=GPT-4o-mini
2026.05
64
80.7
MemSkill
LLM Backbone=GPT-4o-mini
2026.05
57.9
77.9
MemoryOS
LLM Backbone=GPT-4o-mini
2026.05
47.7
59.2
A-MEM
LLM Backbone=GPT-4o-mini
2026.05
43.3
54.7
HAGE
LLM Backbone=Qwen2.5-3B
2026.05
42.9
52.7
MemoryOS
LLM Backbone=Qwen2.5-3B
2026.05
35
45.9
MAGMA
LLM Backbone=Qwen2.5-3B
2026.05
33.7
42.4
A-MEM
LLM Backbone=Qwen2.5-3B
2026.05
18.6
41.6
MemSkill
LLM Backbone=Qwen2.5-3B
2026.05
17.9
24.7
Nemori
LLM Backbone=GPT-4o-mini
2026.05
13.1
62.4
Nemori
LLM Backbone=Qwen2.5-3B
2026.05
9.1
33.2
Feedback
Search any
task
Search any
task