ML Research Wiki / Benchmarks / Conversational Question Answering / ConvFinQA

ConvFinQA

Conversational Question Answering Benchmark

Performance Over Time

📊 Showing 2 results | 📏 Metric: Execution Accuracy

Click "Edit" next to any result to modify it, or add a new result at the bottom. All changes will be reviewed before going live.

Yellow rows = Pending edits Green rows = Pending new results

Model	Paper	Execution Accuracy	Date	Actions
APOLLO	APOLLO: An Optimized Training Approach for Long-f…	77.19	2022-12-14
FinQANet (RoBERTa-large)	ConvFinQA: Exploring the Chain of Numerical Reaso…	68.24	2022-10-07

Rank	Model	Paper	Execution Accuracy	Date	Code
1	APOLLO	APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning	77.19	2022-12-14	📦 gasolsun36/iter-cot 📦 gasolsun36/dynamicrag 📦 gasolsun36/apollo
2	FinQANet (RoBERTa-large)	ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering	68.24	2022-10-07	📦 czyssrs/convfinqa

2022

APOLLO

gasolsun36/iter-cot gasolsun36/dynamicrag gasolsun36/apollo

2022

FinQANet (RoBERTa-large)

czyssrs/convfinqa