opp115_international_and_specific_audiences
- Task Description: Classify whether a clause from a privacy policy describes practices that pertain only to a specific group of users.
- Task Type: Binary classification
- Document Type: privacy policy
- Number of Samples: 988
- Input Length Range: 10-442 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 | 0.968 | 0.968 | 0.492 | 0.968 | 0.032 | 2025-07-25 | View |
| 2 | google/gemma-2-27b-it | 0.917 | 0.918 | 0.917 | 0.917 | 1.000 | 2025-07-24 | View |
| 3 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.914 | 0.914 | 0.914 | 0.914 | 1.000 | 2025-07-25 | View |
| 4 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.899 | 0.899 | 0.898 | 0.899 | 1.000 | 2025-08-03 | View |
| 5 | gpt-4o-mini | 0.892 | 0.892 | 0.891 | 0.892 | 1.000 | 2025-07-02 | View |
| 6 | claude-3-5-haiku-20241022 | 0.746 | 0.746 | 0.736 | 0.746 | 0.997 | 2025-08-01 | View |
| 7 | gpt-4.1-nano | 0.499 | 0.501 | 0.335 | 0.499 | 1.000 | 2025-07-03 | View |