maud_fls_(mae)_standard
- Task Description: The model must select the answer that best characterizes the Forward Looking Standard (FLS) with respect to Material Adverse Effect (MAE) from an excerpt of a merger agreement.
- Task Type: Binary classification
- Document Type: merger agreement
- Number of Samples: 78
- Input Length Range: 623-1559 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: interpretation, merger agreement
- 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 | 0.818 | 0.358 | 0.374 | 0.818 | 1.000 | 2025-07-25 | View |
| 2 | gpt-4o-mini | 0.779 | 0.250 | 0.219 | 0.779 | 1.000 | 2025-07-02 | View |
| 3 | claude-3-5-haiku-20241022 | 0.779 | 0.264 | 0.250 | 0.779 | 1.000 | 2025-08-01 | View |
| 4 | google/gemma-2-27b-it | 0.779 | 0.250 | 0.219 | 0.779 | 1.000 | 2025-07-24 | View |
| 5 | claude-3-haiku-20240307 | 0.779 | 0.250 | 0.219 | 0.779 | 1.000 | 2025-07-28 | View |
| 6 | gpt-4.1-nano | 0.623 | 0.214 | 0.224 | 0.623 | 1.000 | 2025-07-03 | View |
| 7 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.182 | 0.250 | 0.079 | 0.182 | 1.000 | 2025-08-03 | View |