Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Token-level identification of extractive spans on QuoteSum (test)
Loading...
96
Precision
GPT-4
91.84
92.92
94
95.08
May 28, 2024
Precision
Recall
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
GPT-4
2024.05
96
87
90
Llama-7b
2024.05
96
97
96
Mistral-7b
2024.05
94
98
96
Yi-6b
2024.05
94
99
96
OPT-350m
2024.05
94
99
96
GPT-3.5
2024.05
92
46
56
Feedback
Search any
task
Search any
task