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

Zero-shot Language Evaluation on 7-Task Suite (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-E, ARC-C, OBQA) (test)

62.9BoolQ Accuracy

Mamba-2 FP16

55.72457.58759.4561.313Jun 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
62.973.759.961.160.433.237.455.5
2026.06
6068.847.355.94826.332.248.4
2026.06
56.768.837.755.854.924.219.645.4
2026.06
5669.347.556.348.225.933.848.1