Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact Retrieval on Gov Report
Loading...
24.4
F1 Score
OpenOrca
18.576
20.088
21.6
23.112
Apr 14, 2026
F1 Score
Win Rate
Updated 3d ago
Evaluation Results
Method
Method
Links
F1 Score
Win Rate
OpenOrca
context_window=8k
2026.04
24.4
41
Nous Hermes
context_window=32k
2026.04
23.8
37
Full Context
variant=left
2026.04
23.4
45
Thought-Retriever
retriever=Contriever,...
2026.04
23.2
50
Qwen3-Embed-8b
type=retriever-based,...
2026.04
22.9
42
IRCoT
type=retriever-based,...
2026.04
22.5
41
Contriever
type=retriever-based,...
2026.04
22.3
40
Full Context
variant=right
2026.04
22
40
RECOMP
type=retriever-based,...
2026.04
21.5
35
BM25
type=retriever-based,...
2026.04
21.1
30
DRAGON
type=retriever-based,...
2026.04
21
40
TF-IDF
type=retriever-based,...
2026.04
19.5
35
DPR
type=retriever-based,...
2026.04
18.8
20
Feedback
Search any
task
Search any
task