maud_ordinary_course_efforts_standard
- Task Description: The model must select the answer that best characterizes the efforts standard in a merger agreement excerpt.
- Task Type: 3-way classification
- Document Type: merger agreement
- Number of Samples: 182
- Input Length Range: 33-591 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: corporate law, interpretation
- 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 | 0.906 | 0.929 | 0.901 | 0.906 | 1.000 | 2025-08-01 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.641 | 0.655 | 0.636 | 0.641 | 1.000 | 2025-07-25 | View |
| 3 | gpt-4o-mini | 0.492 | 0.655 | 0.496 | 0.492 | 1.000 | 2025-07-02 | View |
| 4 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.486 | 0.635 | 0.482 | 0.486 | 1.000 | 2025-08-03 | View |
| 5 | google/gemma-2-27b-it | 0.475 | 0.619 | 0.474 | 0.475 | 1.000 | 2025-07-24 | View |
| 6 | gpt-4.1-nano | 0.464 | 0.600 | 0.462 | 0.464 | 1.000 | 2025-07-03 | View |
| 7 | claude-3-haiku-20240307 | 0.420 | 0.492 | 0.368 | 0.420 | 1.000 | 2025-07-25 | View |