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

MetaMathQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMetaMathQA
Score89.57
54
Instruction Fine-tuningMetaMathQA Fine-tuning Evaluation Suite (ARC-C, PIQA, MMLU, HE, GSM8K) (test)
ARC-C Accuracy51.45
32
Mathematical ReasoningMetaMathQA (test)
Accuracy53.37
26
Mathematical Question AnsweringMetaMathQA (final)
Accuracy92.52
9
Mathematical ReasoningMetaMathQA 100k-samples
Loss0.142
5
Showing 5 of 5 rows