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

Narrative Understanding on MC-T

93.3First-Token Accuracy

Zephyr-7B

58.77267.73676.785.664May 21, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
93.3
2025.05
93.3
2025.05
92.8
2025.05
92.4
2025.05
91.9
2025.05
91.5
2025.05
91
2025.05
91
2025.05
90
2025.05
89.7
2025.05
88.3
2025.05
86.1
2025.05
86.1
2025.05
85.2
2025.05
85.1
2025.05
82.5
2025.05
82.5
2025.05
82.1
2025.05
82
2025.05
78.5
2025.05
77.1
2025.05
72.2
2025.05
69.1
2025.05
60.1