# Financial Open-ended Question Answering on FinQA (test) Source: [Financial Open-ended Question Answering on FinQA (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:34.079Z Evaluation of model performance on the test split of the FinQA dataset for Financial Open-ended Question Answering, measured using Token Perplexity. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Financial Open-ended Question Answering | | Dataset (including any stated split) | FinQA (test) | | Metric | Token Perplexity | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Token Perplexity](): Lower is better; unit: SCALAR. ## Recorded results | Method | Token Perplexity | Result date | Report paper | | --- | --- | --- | --- | | DEEPFUSION | 3.9697 | Not recorded | 6993f6419ebc499c97409c62 | | DEEPFUSION | 3.97 | Not recorded | 6993f6419ebc499c97409c62 | | FedJETS | 3.9717 | Not recorded | 6993f6419ebc499c97409c62 | | DEEPFUSION | 3.9723 | Not recorded | 6993f6419ebc499c97409c62 | | DEEPFUSION | 3.9774 | Not recorded | 6993f6419ebc499c97409c62 | | FedKMT | 3.9811 | Not recorded | 6993f6419ebc499c97409c62 | | FedJETS | 3.9863 | Not recorded | 6993f6419ebc499c97409c62 | | FedKMT | 3.9908 | Not recorded | 6993f6419ebc499c97409c62 | | FedKMT | 3.9941 | Not recorded | 6993f6419ebc499c97409c62 | | FedJETS | 3.9987 | Not recorded | 6993f6419ebc499c97409c62 | | FedJETS | 4.0006 | Not recorded | 6993f6419ebc499c97409c62 | | FedKMT | 4.003 | Not recorded | 6993f6419ebc499c97409c62 | | OFA-KD | 4.0224 | Not recorded | 6993f6419ebc499c97409c62 | | OFA-KD | 4.0333 | Not recorded | 6993f6419ebc499c97409c62 | | OFA-KD | 4.0375 | Not recorded | 6993f6419ebc499c97409c62 | | OFA-KD | 4.0398 | Not recorded | 6993f6419ebc499c97409c62 | ### DEEPFUSION Token Perplexity: 3.9697. Result ID: 699a96955698665ec421b903. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"16"}. This record does not assert independent reproduction. ### DEEPFUSION Token Perplexity: 3.97. Result ID: 699a96955698665ec421b904. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"32"}. This record does not assert independent reproduction. ### FedJETS Token Perplexity: 3.9717. Result ID: 699a96955698665ec421b8f7. [Reporting paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"16"}. This record does not assert independent reproduction. ### DEEPFUSION Token Perplexity: 3.9723. Result ID: 699a96955698665ec421b906. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"128"}. This record does not assert independent reproduction. ### DEEPFUSION Token Perplexity: 3.9774. Result ID: 699a96955698665ec421b905. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"64"}. This record does not assert independent reproduction. ### FedKMT Token Perplexity: 3.9811. Result ID: 699a96955698665ec421b8fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"32"}. This record does not assert independent reproduction. ### FedJETS Token Perplexity: 3.9863. Result ID: 699a96955698665ec421b8f8. [Reporting paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"32"}. This record does not assert independent reproduction. ### FedKMT Token Perplexity: 3.9908. Result ID: 699a96955698665ec421b8fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"16"}. This record does not assert independent reproduction. ### FedKMT Token Perplexity: 3.9941. Result ID: 699a96955698665ec421b8fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"64"}. This record does not assert independent reproduction. ### FedJETS Token Perplexity: 3.9987. Result ID: 699a96955698665ec421b8f9. [Reporting paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"64"}. This record does not assert independent reproduction. ### FedJETS Token Perplexity: 4.0006. Result ID: 699a96955698665ec421b8fa. [Reporting paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"128"}. This record does not assert independent reproduction. ### FedKMT Token Perplexity: 4.003. Result ID: 699a96955698665ec421b8fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"128"}. This record does not assert independent reproduction. ### OFA-KD Token Perplexity: 4.0224. Result ID: 699a96955698665ec421b901. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"64"}. This record does not assert independent reproduction. ### OFA-KD Token Perplexity: 4.0333. Result ID: 699a96955698665ec421b902. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"128"}. This record does not assert independent reproduction. ### OFA-KD Token Perplexity: 4.0375. Result ID: 699a96955698665ec421b8ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"16"}. This record does not assert independent reproduction. ### OFA-KD Token Perplexity: 4.0398. Result ID: 699a96955698665ec421b900. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of participating edge devices (N)":"32"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.