privacy_policy_entailment
- Task Description: Determine if the description of a privacy policy clause is correct.
- Task Type: Binary classification
- Document Type: privacy policy
- Number of Samples: 4343
- Input Length Range: 5-751 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: interpretation, privacy law
- 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 | claude-3-haiku-20240307 | 0.826 | 0.511 | 0.486 | 0.826 | 0.509 | 2025-07-25 | View |
| 2 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.796 | 0.873 | 0.717 | 0.796 | 0.998 | 2025-08-03 | View |
| 3 | claude-3-5-haiku-20241022 | 0.789 | 0.821 | 0.698 | 0.789 | 0.985 | 2025-08-01 | View |
| 4 | google/gemma-2-27b-it | 0.776 | 0.820 | 0.686 | 0.776 | 1.000 | 2025-07-24 | View |
| 5 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.726 | 0.701 | 0.611 | 0.726 | 1.000 | 2025-07-25 | View |
| 6 | gpt-4.1-nano | 0.710 | 0.590 | 0.552 | 0.710 | 1.000 | 2025-07-03 | View |
| 7 | gpt-4o-mini | 0.658 | 0.794 | 0.597 | 0.658 | 1.000 | 2025-07-02 | View |