Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generative Question Answering on SQuAD Clean (test)
Loading...
72.84
Exact Match (EM)
SDBN-p
53.1632
58.2716
63.38
68.4884
Jun 9, 2026
Exact Match (EM)
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
F1 Score
SDBN-p
Model=Qwen-2.5-7B, PEF...
2026.06
72.84
-
EDA
Model=Qwen-2.5-7B, PEF...
2026.06
59.48
-
NEFTune
Model=Qwen-2.5-7B, PEF...
2026.06
58.12
-
Vanilla
Model=Qwen-2.5-7B, PEF...
2026.06
58
-
SDBN
Backbone=DeBERTa-v3, T...
2026.06
57.8
72.2
Vanilla
Backbone=DeBERTa-v3, T...
2026.06
55
69.8
NEFTune
Backbone=DeBERTa-v3, T...
2026.06
55
69.6
FreeLB
Model=Qwen-2.5-7B, PEF...
2026.06
53.92
-
Feedback
Search any
task
Search any
task