Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on ConFiQA MR
Loading...
89.6
F1 Score
ProbeRAG
57.256
65.653
74.05
82.447
Oct 14, 2025
F1 Score
EM Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
EM Score
ProbeRAG
Architecture=Qwen2.5-7...
2025.10
89.6
86.2
ProbeRAG
Architecture=LLaMA-2-7...
2025.10
80.2
77
CANOE
Architecture=LLaMA-2-7...
2025.10
75.2
72.6
CANOE
Architecture=Qwen2.5-7...
2025.10
71.7
67.8
Context-DPO
Architecture=Qwen2.5-7...
2025.10
71.1
58.8
Context-DPO
Architecture=LLaMA-2-7...
2025.10
58.5
32.7
Feedback
Search any
task
Search any
task