learned_hands_health
- Task Description: Classify if a user post implicates legal issues related to health.
- Task Type: Binary classification
- Document Type: legal question
- Number of Samples: 232
- Input Length Range: 47-2113 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: health law, issue spotting
- 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-3-5-haiku-20241022 | 0.929 | 0.929 | 0.929 | 0.929 | 0.996 | 2025-08-01 | View |
| 2 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.885 | 0.885 | 0.884 | 0.885 | 1.000 | 2025-08-02 | View |
| 3 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.836 | 0.836 | 0.836 | 0.836 | 1.000 | 2025-07-25 | View |
| 4 | google/gemma-2-27b-it | 0.540 | 0.540 | 0.428 | 0.540 | 1.000 | 2025-07-24 | View |
| 5 | claude-3-haiku-20240307 | 0.538 | 0.536 | 0.465 | 0.538 | 0.996 | 2025-07-25 | View |
| 6 | gpt-4o-mini | 0.500 | 0.500 | 0.333 | 0.500 | 1.000 | 2025-07-02 | View |
| 7 | gpt-4.1-nano | 0.469 | 0.469 | 0.401 | 0.469 | 1.000 | 2025-07-03 | View |