maud_fiduciary_exception__board_determination_standard
- Task Description: The model must select the answer that best characterizes the circumstances under which the Board could take actions on a different acquisition proposal notwithstanding the no-shop provision in a merger agreement.
- Task Type: 9-way classification
- Document Type: merger agreement
- Number of Samples: 180
- Input Length Range: 142-786 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 | 0.609 | 0.751 | 0.497 | 0.609 | 1.000 | 2025-08-01 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.117 | 0.122 | 0.128 | 0.117 | 1.000 | 2025-07-25 | View |
| 3 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.101 | 0.090 | 0.122 | 0.101 | 1.000 | 2025-08-03 | View |
| 4 | google/gemma-2-27b-it | 0.056 | 0.203 | 0.171 | 0.056 | 1.000 | 2025-07-24 | View |
| 5 | claude-3-haiku-20240307 | 0.045 | 0.023 | 0.037 | 0.045 | 1.000 | 2025-07-25 | View |
| 6 | gpt-4.1-nano | 0.006 | 0.002 | 0.003 | 0.006 | 1.000 | 2025-07-03 | View |
| 7 | gpt-4o-mini | 0.000 | 0.000 | 0.000 | 0.000 | 1.000 | 2025-07-02 | View |