contract_nli_sharing_with_employees
- Task Description: Determine whether a clause from an NDA allows the Receiving Party to share Confidential Information with its employees.
- Task Type: Binary classification
- Document Type: contract clause
- Number of Samples: 178
- Input Length Range: 19-505 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: contract law, interpretation
- Paper: LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Dataset Download: https://hazyresearch.stanford.edu/legalbench/
7 submissions
Rank | Model | accuracy | balanced_accuracy | f1_macro | f1_micro | valid_predictions_ratio | Date | Results |
---|---|---|---|---|---|---|---|---|
1 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.965 | 0.965 | 0.965 | 0.965 | 1.000 | 2025-07-24 | View |
2 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.953 | 0.951 | 0.952 | 0.953 | 0.994 | 2025-07-29 | View |
3 | claude-3-haiku-20240307 | 0.913 | 0.500 | 0.477 | 0.913 | 0.135 | 2025-07-25 | View |
4 | google/gemma-2-27b-it | 0.828 | 0.814 | 0.818 | 0.828 | 0.959 | 2025-07-24 | View |
5 | gpt-4o-mini | 0.647 | 0.635 | 0.593 | 0.647 | 1.000 | 2025-07-02 | View |
6 | claude-3-5-haiku-20241022 | 0.565 | 0.549 | 0.449 | 0.565 | 1.000 | 2025-08-01 | View |
7 | gpt-4.1-nano | 0.518 | 0.500 | 0.341 | 0.518 | 1.000 | 2025-07-03 | View |