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

Scientific

Benchmarks

Task NameDataset NameSOTA ResultTrend
Scientific ReasoningSCIENTIFIC
Accuracy82.8
36
Generative RecommendationScientific
Recall@53
10
Next item predictionScientific
Hit@143.38
8
Text SummarizationScientific (test)
ROUGE-133.72
6
Scientific/Knowledge ReasoningScientific GPQA and MMLU
Score65.2
4
RecommendationScientific
N@102.61
4
Sequential RecommendationScientific
Epochs13
3
Showing 7 of 7 rows