oral_argument_question_purpose
- Task Description: Given a question asked during oral argument, classify the purpose of the question.
- Task Type: 7-way classification
- Document Type: oral argument
- Number of Samples: 319
- Input Length Range: 2-509 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-3.1-70B-Instruct-Turbo | 0.442 | 0.369 | 0.382 | 0.442 | 1.000 | 2025-07-25 | View |
| 2 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.442 | 0.335 | 0.347 | 0.442 | 1.000 | 2025-08-03 | View |
| 3 | claude-3-5-haiku-20241022 | 0.386 | 0.281 | 0.295 | 0.386 | 0.997 | 2025-08-01 | View |
| 4 | google/gemma-2-27b-it | 0.376 | 0.302 | 0.313 | 0.376 | 0.997 | 2025-07-24 | View |
| 5 | gpt-4o-mini | 0.311 | 0.221 | 0.203 | 0.311 | 1.000 | 2025-07-02 | View |
| 6 | claude-3-haiku-20240307 | 0.287 | 0.208 | 0.211 | 0.287 | 0.984 | 2025-07-25 | View |
| 7 | gpt-4.1-nano | 0.276 | 0.248 | 0.208 | 0.276 | 1.000 | 2025-07-03 | View |