Math Word Problem Solving On Mawps

Metriken

Accuracy (%)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy (%)	Paper Title	Repository
GPT-J + CC	9.3	-	-
GTS with RoBERTa	88.5	Are NLP Models really able to Solve Simple Math Word Problems?
ATHENA (roberta-base)	92.2	ATHENA: Mathematical Reasoning with Thought Expansion
Graph2Tree	83.7	Graph-to-Tree Learning for Solving Math Word Problems
Graph2Tree with RoBERTa	88.7	Are NLP Models really able to Solve Simple Math Word Problems?
MsAT-DeductReasoner	94.3	Learning Multi-Step Reasoning by Solving Arithmetic Tasks
GPT-3.5 turbo (175B)	80.3	Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
DeBERTa (PM + VM)	91.0	Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
EPT	88.7	EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers
Exp-Tree	92.3	An Expression Tree Decoding Strategy for Mathematical Equation Generation
ATHENA (roberta-large)	93	ATHENA: Mathematical Reasoning with Thought Expansion
EPT-X	84.57	EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers
OPT (66B)	7.9	-	-
GPT-3 (175B)	19.8	-	-
OpenMath-CodeLlama-70B (w/ code)	95.7	OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
GPT-J	9.9	Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
EPT	84.51	Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model
Roberta-DeductReasoner	92	Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
GPT-3 text-babbage-001 (6.7B)	2.76	Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
Toolformer	44.0	-	-

0 of 25 row(s) selected.