definition_classification
- Task Description: Given a sentence from a Supreme Court opinion, classify whether or not that sentence offers a definition of a term.
- Task Type: Binary classification
- Document Type: judicial text
- Number of Samples: 1345
- Input Length Range: 6-468 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: judicial text, rhetorical understanding
- 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-3.1-405B-Instruct-Turbo | 0.952 | 0.954 | 0.952 | 0.952 | 1.000 | 2025-07-30 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.950 | 0.951 | 0.950 | 0.950 | 1.000 | 2025-07-25 | View |
| 3 | claude-3-5-haiku-20241022 | 0.947 | 0.947 | 0.947 | 0.947 | 0.993 | 2025-08-01 | View |
| 4 | gpt-4o-mini | 0.945 | 0.946 | 0.945 | 0.945 | 1.000 | 2025-07-02 | View |
| 5 | google/gemma-2-27b-it | 0.936 | 0.935 | 0.936 | 0.936 | 1.000 | 2025-07-24 | View |
| 6 | claude-3-haiku-20240307 | 0.909 | 0.750 | 0.807 | 0.909 | 0.008 | 2025-07-25 | View |
| 7 | gpt-4.1-nano | 0.864 | 0.863 | 0.864 | 0.864 | 1.000 | 2025-07-03 | View |