- h
financebench
- huggingface.co
Updated Oct 25, 2024
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteVirat Singh (2024). financebench [Dataset]. https://huggingface.co/datasets/virattt/financebenchCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedOct 25, 2024AuthorsVirat SinghLicenseApache License, v2.0https://www.apache.org/licenses/LICENSE-2.0
License information was derived automaticallyDescriptionDataset Card for Processed FinanceBench
Dataset DescriptionThis dataset is derived from the PatronusAI/financebench-test dataset, containing only the PASS examples processed into a clean format for question-answering tasks in the financial domain.
Dataset SummaryThe dataset contains financial questions, their corresponding document contexts, and human-written answers that have been verified as faithful to the source documents.
Columns:question:… See the full description on the dataset page: https://huggingface.co/datasets/virattt/financebench.
- h
FinanceBench
- huggingface.co
Updated Oct 9, 2024+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteFinMTEB (2024). FinanceBench [Dataset]. https://huggingface.co/datasets/FinanceMTEB/FinanceBenchCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedOct 9, 2024Dataset authored and provided byFinMTEBDescriptionFinanceMTEB/FinanceBench dataset hosted on Hugging Face and contributed by the HF Datasets community
financebench
- huggingface.co
Updated Mar 1, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteDataRobot Research (2025). financebench [Dataset]. https://huggingface.co/datasets/DataRobot-Research/financebenchDataset updatedMar 1, 2025Dataset provided byDataRobot, Inc.AuthorsDataRobot ResearchLicenseApache License, v2.0https://www.apache.org/licenses/LICENSE-2.0
License information was derived automaticallyDescriptionDataRobot-Research/financebench dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
mistral-original-financebench
- huggingface.co
Updated Jun 15, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCiteSunitha Ravi (2024). mistral-original-financebench [Dataset]. https://huggingface.co/datasets/sunitha-ravi/mistral-original-financebenchCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedJun 15, 2024AuthorsSunitha RaviDescriptionsunitha-ravi/mistral-original-financebench dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
submissions_public
- huggingface.co
Updated Apr 16, 2025+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteFinanceBench.ai (2025). submissions_public [Dataset]. https://huggingface.co/datasets/financebench/submissions_publicDataset updatedApr 16, 2025Dataset provided byFinanceBench.aiDescriptionfinancebench/submissions_public dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
Financebench
- huggingface.co
Updated Dec 3, 2024+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteJason (2024). Financebench [Dataset]. https://huggingface.co/datasets/jbyhring/FinancebenchCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedDec 3, 2024AuthorsJasonDescriptionjbyhring/Financebench dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
finance-events-latest
- huggingface.co
ShareFacebookTwitterEmailClick to copy linkLink copiedCiteFinanceBench.ai, finance-events-latest [Dataset]. https://huggingface.co/datasets/financebench/finance-events-latestDataset provided byFinanceBench.aiDescriptionfinancebench/finance-events-latest dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
financebench-numerical-fixed
- huggingface.co
ShareFacebookTwitterEmailClick to copy linkLink copiedCiteGuangxuan Xu, financebench-numerical-fixed [Dataset]. https://huggingface.co/datasets/gx-ai-architect/financebench-numerical-fixedAuthorsGuangxuan XuDescriptiongx-ai-architect/financebench-numerical-fixed dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
finance-bench-stock-predictions
- huggingface.co
Updated Apr 18, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteStarNeit (2025). finance-bench-stock-predictions [Dataset]. https://huggingface.co/datasets/StarNeit/finance-bench-stock-predictionsDataset updatedApr 18, 2025AuthorsStarNeitDescriptionStarNeit/finance-bench-stock-predictions dataset hosted on Hugging Face and contributed by the HF Datasets community
- h
r1_annotated_finqa_OT7B_eval_7e69
- huggingface.co
+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteML Foundations Development, r1_annotated_finqa_OT7B_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/r1_annotated_finqa_OT7B_eval_7e69Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/r1_annotated_finqa_OT7B_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 50.97% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 50.97% 210 412
- h
OpenThinker2-7B_eval_7e69
- huggingface.co
Updated Apr 15, 2025+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteML Foundations Development (2025). OpenThinker2-7B_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/OpenThinker2-7B_eval_7e69Dataset updatedApr 15, 2025Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/OpenThinker2-7B_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 43.69% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 43.69% 180 412
- h
Qwen2.5-7B-Instruct_eval_7e69
- huggingface.co
ShareFacebookTwitterEmailClick to copy linkLink copiedCiteML Foundations Development, Qwen2.5-7B-Instruct_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/Qwen2.5-7B-Instruct_eval_7e69Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/Qwen2.5-7B-Instruct_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 30.58% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 30.58% 126 412
- h
DeepSeek-R1-Distill-Qwen-7B_eval_7e69
- huggingface.co
+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteDeepSeek-R1-Distill-Qwen-7B_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/DeepSeek-R1-Distill-Qwen-7B_eval_7e69Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/DeepSeek-R1-Distill-Qwen-7B_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 34.22% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 34.22% 141 412
- h
OpenR1-Math-Raw-all-correct-sharegpt_1744357704_eval_7e69
- huggingface.co
Updated May 9, 2025+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteML Foundations Development (2025). OpenR1-Math-Raw-all-correct-sharegpt_1744357704_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/OpenR1-Math-Raw-all-correct-sharegpt_1744357704_eval_7e69Dataset updatedMay 9, 2025Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/OpenR1-Math-Raw-all-correct-sharegpt_1744357704_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 0.00% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 0.00% 0 10
- h
OpenR1-Math-Raw-all-correct-5k_OT7B_eval_7e69
- huggingface.co
Updated Apr 27, 2025+ more versionsShareFacebookTwitterEmailClick to copy linkLink copiedCiteML Foundations Development (2025). OpenR1-Math-Raw-all-correct-5k_OT7B_eval_7e69 [Dataset]. https://huggingface.co/datasets/mlfoundations-dev/OpenR1-Math-Raw-all-correct-5k_OT7B_eval_7e69Dataset updatedApr 27, 2025Dataset authored and provided byML Foundations DevelopmentDescriptionmlfoundations-dev/OpenR1-Math-Raw-all-correct-5k_OT7B_eval_7e69
Precomputed model outputs for evaluation.
Evaluation Results FinanceBenchAverage Accuracy: 45.15% ± 0.00% Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 45.15% 186 412
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailApache License, v2.0https://www.apache.org/licenses/LICENSE-2.0
License information was derived automatically
Dataset Card for Processed FinanceBench
Dataset Description
This dataset is derived from the PatronusAI/financebench-test dataset, containing only the PASS examples processed into a clean format for question-answering tasks in the financial domain.
Dataset Summary
The dataset contains financial questions, their corresponding document contexts, and human-written answers that have been verified as faithful to the source documents.
Columns:
question:… See the full description on the dataset page: https://huggingface.co/datasets/virattt/financebench.