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

Multi-Task Instruct-Tuning on SuperNI (test)

57.35ROUGE Score

BADIT

41.978845.969449.9653.9506May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
57.350.54--
2026.05
55.870.92--
2026.05
55.220.91--
2026.05
55.16-1.35--
2026.05
54.78-1.05--
2026.05
54.78-0.91--
2026.05
54.750.79--
2026.05
54.64-0.57--
2026.05
54.53-0.45--
2026.05
54.33-1.78--
2026.05
54.29-1.88--
2026.05
54.22-1.66--
2026.05
54.2-1.78--
2026.05
53.63-0.68--
2026.05
53.60.7--
2026.05
53.57-2.3--
2026.05
53.50.15--
2026.05
53.31-1.24--
2026.05
53.24-1.33--
2026.05
52.95-1.96--
2026.05
52.89-0.41--
2026.05
52.88-0.72--
2026.05
52.87-0.45--
2026.05
52.71-2.13--
2026.05
52.58-1.02--
2026.05
51.82-0.87--
2026.05
51.72-1.3--
2026.05
51.450.61--
2026.05
51.36-1.05--
2026.05
51.26-1.7--
2026.05
50.96-1.28--
2026.05
50.860.446.95-5.43
2026.05
50.740.625.95-4.21
2026.05
50.07-0.23--
2026.05
49.83-0.47--
2026.05
49.72-0.59--
2026.05
49.64-0.27--
2026.05
49.6-0.23--
2026.05
48.831.718.57-3.49
2026.05
48.58-0.748.5-6.25
2026.05
48.57-1.158.73-6.78
2026.05
48.54-1.318.53-6.68
2026.05
48.44-0.738.96-6.42
2026.05
48.340.3910.31-8.45
2026.05
48.26-0.648.05-6.12
2026.05
48.130.716.25-2.57
2026.05
48.07-1.268.47-6.23
2026.05
48.07-1.268.47-6.23
2026.05
47.83-1.778.78-6.47
2026.05
47.69-0.067.5-6.83
2026.05
47.08-0.119.21-8.11
2026.05
46.980.1711.99-10.11
2026.05
46.8-0.3210.46-9.38
2026.05
46.760.259.3-7.65
2026.05
46.51-0.6212.62-10.8
2026.05
46.2-0.598.58-3.51
2026.05
46.05-0.6911.2-13.57
2026.05
45.59-0.7410.07-5.95
2026.05
45.49-0.939.13-5.27
2026.05
45.470.2711.78-9.71
2026.05
45.34-0.789.67-5.66
2026.05
45.25011.45-10.01
2026.05
45.23-0.6312.54-10.67
2026.05
45.14-0.179.79-4.91
2026.05
45.04-1.1712.7-10.94
2026.05
44.93-2.2412.27-14.8
2026.05
44.93-1.0310.94-10.55
2026.05
44.88-1.912.41-10.23
2026.05
44.16-0.9211.81-10.27
2026.05
43.88-0.8611.66-9.95
2026.05
43.16-0.0313.21-11.28
2026.05
42.57-1.6512.74-10.57