maud_tail_period_length
- Task Description: The model must read an excerpt from a merger agreement and determine the duration of the Tail Period by selecting the best answer from multiple-choice options.
- Task Type: 5-way classification
- Document Type: merger agreement
- Number of Samples: 180
- Input Length Range: 49-875 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 | gpt-4o-mini | 0.385 | 0.592 | 0.446 | 0.385 | 1.000 | 2025-07-02 | View |
| 2 | gpt-4.1-nano | 0.268 | 0.483 | 0.279 | 0.268 | 1.000 | 2025-07-03 | View |
| 3 | google/gemma-2-27b-it | 0.134 | 0.303 | 0.082 | 0.134 | 1.000 | 2025-07-24 | View |
| 4 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.117 | 0.499 | 0.285 | 0.117 | 1.000 | 2025-07-25 | View |
| 5 | claude-3-haiku-20240307 | 0.084 | 0.166 | 0.062 | 0.084 | 1.000 | 2025-07-25 | View |
| 6 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.028 | 0.150 | 0.040 | 0.028 | 1.000 | 2025-08-03 | View |
| 7 | claude-3-5-haiku-20241022 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 | 2025-08-01 | View |