maud_accuracy_of_target_"general"_r&w:_bringdown_timing_answer
- Task Description: The LLM must read an excerpt from a merger agreement and select the correct timing for when representations and warranties are required according to the bring down provision.
- Task Type: Binary classification
- Document Type: merger agreement
- Number of Samples: 182
- Input Length Range: 61-675 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-3-5-haiku-20241022 | 0.983 | 0.977 | 0.979 | 0.983 | 1.000 | 2025-08-01 | View |
| 2 | gpt-4o-mini | 0.807 | 0.657 | 0.679 | 0.807 | 1.000 | 2025-07-02 | View |
| 3 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.718 | 0.500 | 0.418 | 0.718 | 1.000 | 2025-07-25 | View |
| 4 | google/gemma-2-27b-it | 0.718 | 0.500 | 0.418 | 0.718 | 1.000 | 2025-07-24 | View |
| 5 | claude-3-haiku-20240307 | 0.718 | 0.500 | 0.418 | 0.718 | 1.000 | 2025-07-25 | View |
| 6 | gpt-4.1-nano | 0.646 | 0.545 | 0.546 | 0.646 | 1.000 | 2025-07-03 | View |
| 7 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.641 | 0.494 | 0.483 | 0.641 | 1.000 | 2025-08-03 | View |