APOLLO

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Question AnsweringonFinQA
Execution Accuracy· 2022-12-14
71.07
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249
Question AnsweringonFinQA
Program Accuracy· 2022-12-14
68.94
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249
Question AnsweringonConvFinQA
Execution Accuracy· 2022-12-14
78.76
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249
Question AnsweringonConvFinQA
Program Accuracy· 2022-12-14
77.19
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249
Conversational Question AnsweringonConvFinQA
Execution Accuracy· 2022-12-14
78.76
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249
Conversational Question AnsweringonConvFinQA
Program Accuracy· 2022-12-14
77.19
SOTA
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning arXiv:2212.07249