textualism_tool_dictionaries
- Task Description: Determine if a paragraph from a judicial opinion is applying a form of textualism that relies on the dictionary meaning of terms.
- Task Type: Binary classification
- Document Type: judicial text
- Number of Samples: 111
- Input Length Range: 25-888 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: rhetorical understanding, rhetorical-analysis, statute
- 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 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 2025-08-04 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 1.000 | 1.000 | 1.000 | 1.000 | 0.972 | 2025-07-25 | View |
| 3 | claude-3-5-haiku-20241022 | 0.981 | 0.990 | 0.945 | 0.981 | 1.000 | 2025-08-01 | View |
| 4 | gpt-4o-mini | 0.972 | 0.934 | 0.913 | 0.972 | 1.000 | 2025-07-02 | View |
| 5 | google/gemma-2-27b-it | 0.953 | 0.924 | 0.868 | 0.953 | 1.000 | 2025-07-24 | View |
| 6 | claude-3-haiku-20240307 | 0.925 | 0.556 | 0.580 | 0.925 | 1.000 | 2025-07-25 | View |
| 7 | gpt-4.1-nano | 0.850 | 0.565 | 0.559 | 0.850 | 1.000 | 2025-07-03 | View |