Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational Question Answering on LoCoMo (test)
Loading...
50.7
F1 Score
Full Context
30.108
35.454
40.8
46.146
May 15, 2026
F1 Score
Judge Score
Updated 16d ago
Evaluation Results
Method
Method
Links
F1 Score
Judge Score
Full Context
LLM Backbone=GPT-4.1-MINI
2026.05
50.7
84.8
RecMem
LLM Backbone=GPT-4.1-MINI
2026.05
46.9
81.1
MemoryOS
LLM Backbone=GPT-4O-MINI
2026.05
45.6
63.6
MemoryOS
LLM Backbone=GPT-4.1-MINI
2026.05
44.5
67.6
AMem
LLM Backbone=GPT-4.1-MINI
2026.05
44
69.7
Mem0
LLM Backbone=GPT-4O-MINI
2026.05
42.9
58.6
Mem0
LLM Backbone=GPT-4.1-MINI
2026.05
42.8
62.9
Full Context
LLM Backbone=GPT-4O-MINI
2026.05
42.3
76.4
RecMem
LLM Backbone=GPT-4O-MINI
2026.05
38.5
72.47
AMem
LLM Backbone=GPT-4O-MINI
2026.05
36.4
60.8
Naive Rag
LLM Backbone=GPT-4.1-MINI
2026.05
33.7
54.4
Naive Rag
LLM Backbone=GPT-4O-MINI
2026.05
30.9
49.7
Feedback
Search any
task
Search any
task
