maud_definition_contains_knowledge_requirement_-_answer
- Task Description: The model must select the answer that best characterizes the knowledge requirement in the definition of 'Intervening Event' from a segment of a merger agreement.
- Task Type: 4-way classification
- Document Type: merger agreement
- Number of Samples: 148
- Input Length Range: 50-1128 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 | claude-3-haiku-20240307 | 0.531 | 0.255 | 0.182 | 0.531 | 1.000 | 2025-07-25 | View |
| 2 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.524 | 0.250 | 0.172 | 0.524 | 1.000 | 2025-08-03 | View |
| 3 | google/gemma-2-27b-it | 0.503 | 0.240 | 0.169 | 0.503 | 1.000 | 2025-07-24 | View |
| 4 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.476 | 0.254 | 0.236 | 0.476 | 1.000 | 2025-07-25 | View |
| 5 | gpt-4.1-nano | 0.449 | 0.239 | 0.226 | 0.449 | 1.000 | 2025-07-03 | View |
| 6 | claude-3-5-haiku-20241022 | 0.442 | 0.236 | 0.220 | 0.442 | 1.000 | 2025-08-01 | View |
| 7 | gpt-4o-mini | 0.361 | 0.253 | 0.138 | 0.361 | 1.000 | 2025-07-02 | View |