function_of_decision_section
- Task Description: Classify the function of different sections of legal written opinions.
- Task Type: 7-way classification
- Document Type: judicial text
- Number of Samples: 374
- Input Length Range: 6-704 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 | 0.418 | 0.418 | 0.403 | 0.418 | 0.997 | 2025-08-01 | View |
| 2 | gpt-4o-mini | 0.403 | 0.400 | 0.375 | 0.403 | 1.000 | 2025-07-02 | View |
| 3 | google/gemma-2-27b-it | 0.390 | 0.388 | 0.376 | 0.390 | 0.978 | 2025-07-24 | View |
| 4 | gpt-4.1-nano | 0.337 | 0.343 | 0.293 | 0.337 | 0.986 | 2025-07-03 | View |
| 5 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.324 | 0.324 | 0.285 | 0.324 | 1.000 | 2025-07-30 | View |
| 6 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.311 | 0.308 | 0.254 | 0.311 | 1.000 | 2025-07-25 | View |
| 7 | claude-3-haiku-20240307 | 0.220 | 0.222 | 0.189 | 0.220 | 0.807 | 2025-07-25 | View |