Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Boolean Question Answering on BoolQ (test)

86.7Accuracy (Avg)

QWEN3-14B

51.901660.935869.9779.0042Dec 20, 2022Jun 27, 2023Jan 3, 2024Jul 10, 2024Jan 16, 2025Jul 24, 2025Jan 30, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
86.7--
2026.01
86.42--
2026.01
84.92--
2026.01
83.43--
2026.01
83.33--
2026.01
83.09--
2026.01
78.87--
2026.01
75.47--
2026.01
74.04--
2022.12
69.42.162.8
2022.12
69.33.857.3
2022.12
692.661.5
2026.01
68.65--
2022.12
68.32.362.7
2022.12
682.559.8
2026.01
66.21--
2022.12
66.23.454.6
2026.01
65.69--
2022.12
65.54.951.8
2022.12
65.55.250.4
2022.12
65.20.963.4
2022.12
65.25.649.7
2022.12
65.11.661.1
2022.12
64.85.349.3
2022.12
64.76.449.3
2022.12
63.82.756.4
2022.12
63.72.256
2022.12
63.56.351
2022.12
62.63.355.6
2022.12
62.3354.3
2022.12
61.23.950.4
2022.12
61.2451.1
2022.12
61.23.351.9
2022.12
613.849.7
2022.12
60.83.549.6
2022.12
604.349.5
2026.01
57.4--
2026.01
53.24--