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

Natural Language Inference on HANS evaluated subset

157Rule-bearing

MechaRule (Qwen2-1.5B)

10.3648.4386.5124.57May 4, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2026.05
1570.91111432.214.2
2026.05
330.9242461.219
2026.05
290.9452532.213.2
2026.05
290.9252161.518.6
2026.05
280.9152161.218.8
2026.05
260.9342432.213.4
2026.05
260.8991761.517.6
2026.05
240.9452232.213.5
2026.05
160.931432.211.5