Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Free-form Visual Question Answering on camroll
Loading...
6.33
Judge Score
Oracle
-0.2532
1.4559
3.165
4.8741
Jun 3, 2026
Judge Score
Recall
Updated 1mo ago
Evaluation Results
Method
Method
Links
Judge Score
Recall
Oracle
Base Model=Gemini-2.5-...
2026.06
6.33
100
All images
Base Model=Gemini-2.5-...
2026.06
5.01
100
camroll-agent
Base Model=Gemini-2.5-...
2026.06
4.11
83.1
All captions
Base Model=Gemini-2.5-...
2026.06
3.82
100
ClaudeCode
Base Model=Sonnet-4.6,...
2026.06
3.77
-
Mem0
Base Model=Gemini-2.5-...
2026.06
2.68
75.3
HippoRAG2
Base Model=Gemini-2.5-...
2026.06
2.58
50.1
LightMem
Base Model=Gemini-2.5-...
2026.06
2.44
70.2
Self-RAG
Base Model=LLama-2, Re...
2026.06
2.41
19.8
SimpleMem
Base Model=Gemini-2.5-...
2026.06
1.7
58.6
MemOS
Base Model=Gemini-2.5-...
2026.06
1.09
27.3
Nothing
Base Model=Gemini-2.5-...
2026.06
0
0
Feedback
Search any
task
Search any
task