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

Chemistry

Benchmarks

Task NameDataset NameSOTA ResultTrend
Speculative DecodingChemistry
MAT7.1
30
Scientific ReasoningChemistry
Avg Score @16 (1h)71.6
16
Science Question AnsweringChemistry
Mean@1680.6
9
Success Rate PredictionChemistry Full (OOD)
Success Rate83.9
9
Success Rate PredictionChemistry Jungle OOD
Success Rate8,440
9
Success Rate PredictionChemistry Chain (OOD)
Success Rate82.3
9
Success Rate PredictionChemistry Collider (OOD)
Success Rate97
9
Symbolic RegressionChemistry
Metric0
7
Outlier DetectionChemistry
Precision100
3
Showing 9 of 9 rows