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

Commonsense Reasoning on WG-S

70.9Accuracy

Bayesian-LoRA (S=4)

55.965659.842863.7267.5972Jun 17, 2024Sep 23, 2024Dec 30, 2024Apr 8, 2025Jul 15, 2025Oct 21, 2025Jan 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
70.94.90.79
2024.06
70.8920.620.91
2024.06
69.5728.522.71
2024.06
69.4627.982.79
2024.06
69.24.150.6
2024.06
69.079.350.63
2026.01
69.079.350.63
2024.06
68.9929.833.17
2024.06
68.6229.762.46
2026.01
6830.82.75
2026.01
6712.80.68
2026.01
66.911.60.68
2026.01
66.97.80.66
2026.01
66.729.52.54
2026.01
66.725.21.31
2024.06
66.310.890.68
2024.06
56.5421.811.4
2026.01
56.5421.811.4