ML Research Wiki / Benchmarks / Math Word Problem Solving / Math23K

Math23K

Math Word Problem Solving Benchmark

Performance Over Time

📊 Showing 12 results | 📏 Metric: Accuracy (5-fold)

Top Performing Models

Rank Model Paper Accuracy (5-fold) Date Code
1 GPT-4 (Teaching-Inspired) Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models 94.30 2024-10-10 📦 sallytan13/teaching-inspired-prompting
2 ATHENA (roberta-large) ATHENA: Mathematical Reasoning with Thought Expansion 86.50 2023-11-02 📦 the-jb/athena-math
3 Multi-view* (ours) 📚 Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem 85.20 2022-10-21 📦 zwq2018/multi-view-consistency-for-mwp
4 ATHENA (roberta-base) ATHENA: Mathematical Reasoning with Thought Expansion 84.40 2023-11-02 📦 the-jb/athena-math
5 Generate and Rank Generate & Rank: A Multi-task Framework for Math Word Problems 84.30 2021-09-07 -
6 Exp-Tree An Expression Tree Decoding Strategy for Mathematical Equation Generation 84.10 2023-10-14 📦 zwq2018/multi-view-consistency-for-mwp
7 Roberta-DeductReasoner Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction 83.00 2022-03-19 📦 allanj/deductive-mwp
8 MWP-BERT MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving 82.40 2021-07-28 📦 lzhenwen/mwp-bert
9 Recall and Learn Recall and Learn: A Memory-augmented Solver for Math Word Problems 80.80 2021-09-27 📦 sfeng-m/real4mwp
10 RoBERTaGen MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers 76.60 2021-09-02 📦 lyh-yf/mwptoolkit

All Papers (12)

sallytan13/teaching-inspired-prompting
the-jb/athena-math
zwq2018/multi-view-consistency-for-mwp
the-jb/athena-math
zwq2018/multi-view-consistency-for-mwp
allanj/deductive-mwp
lzhenwen/mwp-bert
sfeng-m/real4mwp
lyh-yf/mwptoolkit
QinJinghui/SAU-Solver
evelinehong/LBF