Math Word Problem Solving
Benchmark List
All benchmarks related to this task
asdiv-a
Best model: ATHENA (roberta-large)
Metrics
View Details
gsm-plus
Best model: GPT-4
Metrics
View Details
math-minival
Best model: Process Supervision (GPT-4)
Metrics
View Details
math23k
Best model: Roberta-DeductReasoner
Metrics
View Details
mathqa
Best model: ELASTIC (RoBERTa-large)
Metrics
View Details
mawps
Best model: OpenMath-CodeLlama-70B (w/ code)
Metrics
View Details
paramawps
Best model: DeBERTa (VM)
Metrics
View Details
pen
Best model: EPT-X
Metrics
View Details
svamp
Best model: GPT-4 (Teaching-Inspired)
Metrics
View Details
svamp-1-n
Best model: ATHENA (roberta-large)
Metrics
View Details
alg514
Metrics
View Details
draw-1k
Metrics
View Details
math
Metrics
View Details