Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Evidence Retrieval on 2Wiki
Loading...
40.7
Recall@5
INTRA
12.932
20.141
27.35
34.559
May 7, 2026
Recall@5
Recall@10
Recall@20
Updated 26d ago
Evaluation Results
Method
Method
Links
Recall@5
Recall@10
Recall@20
INTRA
2026.05
40.7
50.3
55.2
Qwen3-Emb-4B + Jina reranker
parameters=4B, reranke...
2026.05
35.4
40.3
43.5
Qwen3-Emb-4B
parameters=4B
2026.05
32.8
37.2
40.8
BGE
variant=BGE-large
2026.05
30.9
35.9
40.1
Hybrid RAG
fusion=reciprocal rank...
2026.05
29.1
36
40.9
Qwen3-Emb-0.6B
parameters=0.6B
2026.05
28
33.3
36.8
BM25
type=sparse lexical
2026.05
17.4
23.2
28.4
MaxSim
type=late-interaction,...
2026.05
16.7
22.6
27.5
TF-IDF
type=sparse lexical
2026.05
14
19.3
24.7
Feedback
Search any
task
Search any
task