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

Biology

Benchmarks

Task NameDataset NameSOTA ResultTrend
Speculative DecodingBiology
MAT7.18
30
Link PredictionBiology C.ele (test)
Hits@5068.62
18
Scientific ReasoningBiology
Avg@16 (1h)56.1
16
Program generationexpert-curated Biology dataset
Program Accuracy70.26
10
Science Question AnsweringBiology (Bio.)
Mean@1665.4
9
Symbolic RegressionBiology
Error0
7
Multi-Omics SequenceBiology-Instruction
Score52.5
5
Outlier DetectionBiology
Precision80
3
RetrievalBiology
NDCG@250.336
2
Showing 9 of 9 rows