Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact Retrieval on WCEP
Loading...
23.8
F1 Score
Thought-Retriever
16.624
18.487
20.35
22.213
Apr 14, 2026
F1 Score
Win Rate
Updated 3d ago
Evaluation Results
Method
Method
Links
F1 Score
Win Rate
Thought-Retriever
retriever=Contriever,...
2026.04
23.8
50
Qwen3-Embed-8b
type=retriever-based,...
2026.04
23.5
44
IRCoT
type=retriever-based,...
2026.04
23.3
42
DRAGON
type=retriever-based,...
2026.04
23.1
35
TF-IDF
type=retriever-based,...
2026.04
22.3
34
Nous Hermes
context_window=32k
2026.04
21.4
37
Contriever
type=retriever-based,...
2026.04
21.1
40
Full Context
variant=right
2026.04
21
41
Full Context
variant=left
2026.04
20.7
35
RECOMP
type=retriever-based,...
2026.04
20.5
33
DPR
type=retriever-based,...
2026.04
20.1
33
BM25
type=retriever-based,...
2026.04
17.8
31
OpenOrca
context_window=8k
2026.04
16.9
30
Feedback
Search any
task
Search any
task