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

Mathematical Reasoning on GSM8K (test) (PPL, pass@1, Throughput)

1.25Perplexity (PPL)

AR Transformer

1.2161.44551.6751.9045Jul 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
1.2575.7467.16
2026.07
1.4163.5355.39
2026.07
1.4266.4160.42
2026.07
1.563.9156.5
2026.07
1.5356.9454.67
2026.07
1.5961.9455.08
2026.07
1.6750.4952.18
2026.07
2.16.3724.48