OpenCodePapers
question-answering-on-drop-test
Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
F1
↕
ModelName
ReleaseDate
↕
Question Directed Graph Attention Network for Numerical Reasoning over Text
88.38
QDGAT (ensemble)
2020-09-16
Reasoning Like Program Executors
✓ Link
87.6
POET
2022-01-27
PaLM 2 Technical Report
✓ Link
85.0
PaLM 2 (few-shot)
2023-05-17
Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension
81.78
BERT+Calculator (ensemble)
2019-08-31
Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension
81.71
NeRd
2020-05-01
GPT-4 Technical Report
✓ Link
80.9
GPT-4 (few-shot, k=3)
2023-03-15
A Simple and Effective Model for Answering Multi-span Questions
✓ Link
80.7
TASE-BERT
2019-09-29
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
✓ Link
79.88
MTMSN Large
2019-08-15
Injecting Numerical Reasoning Skills into Language Models
✓ Link
72.4
GenBERT (+ND+TD)
2020-04-09
NumNet: Machine Reading Comprehension with Numerical Reasoning
✓ Link
67.97
NumNet
2019-10-15
GPT-4 Technical Report
✓ Link
64.1
GPT 3.5 (few-shot, k=3)
2023-03-15
Orca 2: Teaching Small Language Models How to Reason
60.26
Orca 2-7B
2023-11-18
Orca 2: Teaching Small Language Models How to Reason
57.97
Orca 2-13B
2023-11-18
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
✓ Link
47.01
NAQA Net
2019-03-01
Language Models are Few-Shot Learners
✓ Link
36.5
GPT-3 175B (few-shot, k=32)
2020-05-28
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
✓ Link
32.7
BERT
2019-03-01