overruling
- Task Description: Classify whether a sentence from a judicial opinion overrules a previous case.
- Task Type: Binary classification
- Document Type: judicial text
- Number of Samples: 2400
- Input Length Range: 1-300 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 | claude-3-5-haiku-20241022 | 0.955 | 0.956 | 0.955 | 0.955 | 1.000 | 2025-08-01 | View |
| 2 | google/gemma-2-27b-it | 0.951 | 0.951 | 0.951 | 0.951 | 1.000 | 2025-07-24 | View |
| 3 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.947 | 0.947 | 0.946 | 0.947 | 1.000 | 2025-08-03 | View |
| 4 | gpt-4o-mini | 0.933 | 0.934 | 0.933 | 0.933 | 1.000 | 2025-07-02 | View |
| 5 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.931 | 0.932 | 0.930 | 0.931 | 1.000 | 2025-07-25 | View |
| 6 | claude-3-haiku-20240307 | 0.909 | 0.910 | 0.908 | 0.909 | 0.957 | 2025-07-25 | View |
| 7 | gpt-4.1-nano | 0.761 | 0.762 | 0.761 | 0.761 | 1.000 | 2025-07-03 | View |