Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
2-Way Classification on BEA Shared Task 2 Track 3 (Unseen Answers) 2026 (Evaluation)
Loading...
0.674
QWK
Meta-prompt best variant per group
0.48472
0.53386
0.583
0.63214
May 11, 2026
QWK
WF1
Rank
Updated 21d ago
Evaluation Results
Method
Method
Links
QWK
WF1
Rank
Meta-prompt best variant per group
selection=best variant...
2026.05
0.674
86.3
14
Meta-prompt thinking medium
thinking_level=medium
2026.05
0.654
85.3
25
Baseline prompting Gemini 3 Flash
model=Gemini 3 Flash,...
2026.05
0.598
83.5
37
Ensemble prompt tuning with Gemini baseline
method=ensemble, base=...
2026.05
0.537
80.9
42
SVM + TF-IDF (2-10)grams
classifier=SVM, featur...
2026.05
0.52
80.6
43
Prompt tuning with synthetic data
augmentation=synthetic...
2026.05
0.492
78.6
44
Feedback
Search any
task
Search any
task