maud_definition_includes_asset_deals
- Task Description: The model must select the answer that best characterizes what qualifies as a superior offer in terms of asset deals from a merger agreement excerpt.
- Task Type: 4-way classification
- Document Type: merger agreement
- Number of Samples: 147
- Input Length Range: 90-1606 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 | 0.452 | 0.311 | 0.275 | 0.452 | 1.000 | 2025-08-01 | View |
| 2 | gpt-4.1-nano | 0.089 | 0.339 | 0.062 | 0.089 | 1.000 | 2025-07-03 | View |
| 3 | gpt-4o-mini | 0.082 | 0.333 | 0.051 | 0.082 | 1.000 | 2025-07-02 | View |
| 4 | claude-3-haiku-20240307 | 0.082 | 0.333 | 0.051 | 0.082 | 1.000 | 2025-07-25 | View |
| 5 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.082 | 0.333 | 0.051 | 0.082 | 1.000 | 2025-08-03 | View |
| 6 | google/gemma-2-27b-it | 0.082 | 0.333 | 0.051 | 0.082 | 1.000 | 2025-07-24 | View |
| 7 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.075 | 0.306 | 0.047 | 0.075 | 1.000 | 2025-07-25 | View |