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

Boolean Question Answering on BoolQ (Accuracy and Speed)

85.9Accuracy

TALE

44.622455.338766.05576.7713Jun 15, 2025Aug 10, 2025Oct 6, 2025Dec 1, 2025Jan 27, 2026Mar 24, 2026May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2025.10
85.912-8.8
2025.10
85.4--
2025.10
85.4--17.6
2025.10
84.416-18.5
2025.10
83.914-13.3
2026.05
83.73--
2025.10
82.7--23.2
2026.05
82.6--
2026.05
82.29--
2025.10
81.9--
2025.10
81.3--
2025.10
80.8--27.7
2026.05
80.61--
2025.06
77.68--
2026.05
74.89--
2025.10
7430-17.2
2025.06
72.81--
2026.05
71.71--
2025.06
71.12--
2025.06
71.1--
2026.05
70.52--
2026.05
70.4--
2026.05
69.72--
2025.06
69.13--
2026.05
67.8--
2025.06
67.77--
2025.06
66.91--
2026.05
66.85--
2026.05
66.73--
2026.05
66.54--
2025.06
66.36--
2026.05
64.86--
2026.05
64.62--
2026.05
64.43--
2025.10
63--54.2
2026.05
62.54--
2026.05
60.98--
2026.05
60.55--
2026.05
60.43--
2026.05
60.24--
2026.05
59.02--
2026.05
58.2--
2026.05
57.92--
2026.05
57.58--
2026.05
57.37--
2026.05
55.72--
2026.05
54.25--
2025.10
53--
2026.05
51.56--
2025.10
51.1--
2025.10
50.43--
2025.10
50.21--
2025.10
49.57--
2025.10
49.42--
2025.10
48.72--
2026.05
46.3--
2025.10
46.21--