learned_hands_benefits
- Task Description: Classify if a user post implicates legal issues related to benefits.
- Task Type: Binary classification
- Document Type: legal question
- Number of Samples: 72
- Input Length Range: 56-1110 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: issue spotting, social services
- 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 | 0.825 | 0.824 | 0.825 | 0.825 | 0.955 | 2025-07-25 | View |
| 2 | claude-3-haiku-20240307 | 0.776 | 0.767 | 0.769 | 0.776 | 0.742 | 2025-07-25 | View |
| 3 | claude-3-5-haiku-20241022 | 0.758 | 0.758 | 0.756 | 0.758 | 1.000 | 2025-08-01 | View |
| 4 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.682 | 0.682 | 0.646 | 0.682 | 1.000 | 2025-07-31 | View |
| 5 | gpt-4.1-nano | 0.515 | 0.515 | 0.366 | 0.515 | 1.000 | 2025-07-03 | View |
| 6 | google/gemma-2-27b-it | 0.515 | 0.515 | 0.366 | 0.515 | 1.000 | 2025-07-24 | View |
| 7 | gpt-4o-mini | 0.500 | 0.500 | 0.333 | 0.500 | 1.000 | 2025-07-02 | View |