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

Financial Question Answering on BizBench SEC-NUM

79.3Accuracy

GPT

25.604839.544953.48567.4251Jun 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
79.3
2026.06
74.7
2026.06
69.85
2026.06
68.65
2026.06
63.64
2026.06
63.39
2026.06
59.32
2026.06
53.46
2026.06
27.67