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

Open-ended Text Generation on PTB

67.7COH Score

DEL

51.0655.3859.764.02Feb 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
67.7
2026.02
66.1
2026.02
66.1
2026.02
65.5
2026.02
65
2026.02
64.5
2026.02
64.2
2026.02
64
2026.02
63.9
2026.02
63.9
2026.02
63.7
2026.02
63.6
2026.02
63.6
2026.02
63.6
2026.02
63.3
2026.02
63
2026.02
62.9
2026.02
62.9
2026.02
62.8
2026.02
62.8
2026.02
62.5
2026.02
62.4
2026.02
62.3
2026.02
62
2026.02
61.8
2026.02
61.7
2026.02
61.7
2026.02
61.5
2026.02
59.8
2026.02
59.3
2026.02
59.2
2026.02
59.2
2026.02
59.2
2026.02
59.2
2026.02
59.1
2026.02
59
2026.02
58.9
2026.02
58.7
2026.02
58.5
2026.02
58.4
2026.02
58.3
2026.02
58.1
2026.02
57.5
2026.02
57.4
2026.02
57.1
2026.02
57
2026.02
57
2026.02
56.8
2026.02
56.7
2026.02
56.6
2026.02
56.5
2026.02
56.5
2026.02
56.1
2026.02
56.1
2026.02
55.8
2026.02
55.8
2026.02
52.6
2026.02
52.6
2026.02
52.5
2026.02
52.2
2026.02
52.1
2026.02
52
2026.02
51.7
2026.02
51.7