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

Open-ended counting on HowMany-QA 1.0 (test)

60.3Accuracy

RCN

30.97238.58646.253.814Oct 29, 2018
Updated 1mo ago

Evaluation Results

MethodLinks
2018.10
60.32.35
2018.10
56.12.45
2018.10
54.72.59
2018.10
45.52.93
2018.10
43.33.66
2018.10
40.53.17
2018.10
37.33.49
2018.10
37.13.51
2018.10
33.83.74
2018.10
32.13.34