| OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset | ✓ Link | 95.7 | OpenMath-CodeLlama-70B (w/ code) | 2024-02-15 |
| Learning Multi-Step Reasoning by Solving Arithmetic Tasks | ✓ Link | 94.3 | MsAT-DeductReasoner | 2023-06-02 |
| ATHENA: Mathematical Reasoning with Thought Expansion | ✓ Link | 93 | ATHENA (roberta-large) | 2023-11-02 |
| Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem | ✓ Link | 92.3 | Multi-view | 2022-10-21 |
| An Expression Tree Decoding Strategy for Mathematical Equation Generation | ✓ Link | 92.3 | Exp-Tree | 2023-10-14 |
| ATHENA: Mathematical Reasoning with Thought Expansion | ✓ Link | 92.2 | ATHENA (roberta-base) | 2023-11-02 |
| Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction | ✓ Link | 92 | Roberta-DeductReasoner | 2022-03-19 |
| Math Word Problem Solving by Generating Linguistic Variants of Problem Statements | ✓ Link | 91.0 | DeBERTa (PM + VM) | 2023-06-24 |
| EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers | ✓ Link | 88.7 | EPT | |
| Are NLP Models really able to Solve Simple Math Word Problems? | ✓ Link | 88.7 | Graph2Tree with RoBERTa | 2021-03-12 |
| Are NLP Models really able to Solve Simple Math Word Problems? | ✓ Link | 88.5 | GTS with RoBERTa | 2021-03-12 |
| Generating Equation by Utilizing Operators : GEO model | | 85.1 | GEO | 2020-12-01 |
| EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers | ✓ Link | 84.57 | EPT-X | |
| Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model | ✓ Link | 84.51 | EPT | |
| Graph-to-Tree Learning for Solving Math Word Problems | ✓ Link | 83.7 | Graph2Tree | 2020-07-01 |
| Llama 2: Open Foundation and Fine-Tuned Chat Models | ✓ Link | 82.4 | LLaMA 2-Chat | 2023-07-18 |
| Math Word Problem Solving by Generating Linguistic Variants of Problem Statements | ✓ Link | 80.3 | GPT-3.5 turbo (175B) | 2023-06-24 |
| []() | | 44.0 | Toolformer | |
| []() | | 19.8 | GPT-3 (175B) | |
| []() | | 15.0 | Toolformer (disabled) | |
| Math Word Problem Solving by Generating Linguistic Variants of Problem Statements | ✓ Link | 9.9 | GPT-J | 2023-06-24 |
| []() | | 9.3 | GPT-J + CC | |
| []() | | 7.9 | OPT (66B) | |
| Math Word Problem Solving by Generating Linguistic Variants of Problem Statements | ✓ Link | 4.09 | GPT-3 text-curie-001 (13B) | 2023-06-24 |
| Math Word Problem Solving by Generating Linguistic Variants of Problem Statements | ✓ Link | 2.76 | GPT-3 text-babbage-001 (6.7B) | 2023-06-24 |