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

Literature

Benchmarks

Task NameDataset NameSOTA ResultTrend
Named Entity RecognitionLiterature
F1 Score72.7
19
Genetic Circuit DesignLiterature-91
Task Success Rate (TSR)44.9
11
Factoid Question AnsweringLiterature factoid QA (test)
Accuracy95.1
9
Part-level Masked Component PredictionLiterature-91
Top-1 Accuracy41.4
3
Function-level Masked Component PredictionLiterature-91
Top-1 Accuracy74.6
3
Type-level Masked Component PredictionLiterature-91
Top-1 Accuracy93.6
3
Genetic circuit rediscoveryLiterature-91 Overall
Pass@142.9
2
Genetic circuit rediscoveryLiterature-91 Extended 41 Complex Circuits
Pass@124.4
2
Named Entity RecognitionLiterature English
F1 Score (%)59.68
2
Showing 9 of 9 rows