Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open-domain QA on HotPotQA top 1000 samples (test)
Loading...
38.6
F1
BIDER
26.328
29.514
32.7
35.886
Feb 19, 2024
F1
Token Count
Updated 4d ago
Evaluation Results
Method
Method
Links
F1
Token Count
BIDER
refinement_type=Abstra...
2024.02
38.6
113
Bge-Reranker
refinement_type=Extrac...
2024.02
38.4
186
Original Prompt
refinement_type=Withou...
2024.02
37.6
770
BART-Summarizer
refinement_type=Abstra...
2024.02
36.9
254
SBERT
refinement_type=Extrac...
2024.02
36
187
BM25
refinement_type=Extrac...
2024.02
35.6
186
LLM-Embedder
refinement_type=Extrac...
2024.02
35.2
186
Selective-Context
refinement_type=Abstra...
2024.02
33.2
234
LongLLMLingua
refinement_type=Abstra...
2024.02
30.2
222
Zero-shot
refinement_type=Withou...
2024.02
26.8
0
Feedback
Search any
task
Search any
task