ML Research Wiki / Benchmarks / Math Word Problem Solving / ParaMAWPS

ParaMAWPS

Math Word Problem Solving Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: Accuracy (%)

Top Performing Models

Rank Model Paper Accuracy (%) Date Code
1 DeBERTa (VM) 📚 Math Word Problem Solving by Generating Linguistic Variants of Problem Statements 79.10 2023-06-24 📦 starscream-11813/variational-mathematical-reasoning
2 DeBERTa DeBERTa: Decoding-enhanced BERT with Disentangled Attention 74.10 2020-06-05 📦 huggingface/transformers 📦 microsoft/DeBERTa 📦 osu-nlp-group/mind2web
3 GPT-3.5 Turbo (175B) Math Word Problem Solving by Generating Linguistic Variants of Problem Statements 73.00 2023-06-24 📦 starscream-11813/variational-mathematical-reasoning
4 GPT-J (6B) Math Word Problem Solving by Generating Linguistic Variants of Problem Statements 5.90 2023-06-24 📦 starscream-11813/variational-mathematical-reasoning
5 GPT-3 text-curie-001 (13B) Math Word Problem Solving by Generating Linguistic Variants of Problem Statements 4.20 2023-06-24 📦 starscream-11813/variational-mathematical-reasoning
6 GPT-3 text-babbage-001 (6.7B) Math Word Problem Solving by Generating Linguistic Variants of Problem Statements 3.21 2023-06-24 📦 starscream-11813/variational-mathematical-reasoning

All Papers (6)

starscream-11813/variational-mathematical-reasoning
huggingface/transformers microsoft/DeBERTa
starscream-11813/variational-mathematical-reasoning
starscream-11813/variational-mathematical-reasoning
starscream-11813/variational-mathematical-reasoning
starscream-11813/variational-mathematical-reasoning