Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering with Abstention on ABSTAIN (test)

78.6Accuracy

DeepSeek-R1

47.60855.65463.771.746Apr 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
78.68.585.952.246.589.1
2026.04
77.810.987.358.450.185.8
2026.04
71.911.581.256.930.754
2026.04
62.412.771.547.22.34.9
2026.04
58.38.563.733.800
2026.04
57.220.471.968.155.180.9
2026.04
48.818.860.19.40.66.4