Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact-driven Question Answering on HotpotQA (F1, EM)
Loading...
60.78
F1 Score
w/t BoT
49.5688
52.4794
55.39
58.3006
May 20, 2026
F1 Score
Exact Match (EM)
Updated 12d ago
Evaluation Results
Method
Method
Links
F1 Score
Exact Match (EM)
w/t BoT
Model=Qwen2.5-1.5b-ins...
2026.05
60.78
47.27
w/t CD
Model=Qwen2.5-1.5b-ins...
2026.05
59.97
46.8
w/t KLE
Model=Qwen2.5-1.5b-ins...
2026.05
57.62
44.31
w/t SE
Model=Qwen2.5-1.5b-ins...
2026.05
57.33
44.18
CARE
Model=Qwen2.5-1.5b-ins...
2026.05
57.03
43.75
GRPO
Model=Qwen2.5-1.5b-ins...
2026.05
50
37.06
Feedback
Search any
task
Search any
task