contract_qa
- Task Description: The LLM must determine if language from a contract contains a particular type of content by answering yes/no questions.
- Task Type: Binary classification
- Document Type: contract clause
- Number of Samples: 88
- Input Length Range: 23-141 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: contract 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-haiku-20240307 | 0.988 | 0.987 | 0.987 | 0.988 | 1.000 | 2025-07-25 | View |
| 2 | google/gemma-2-27b-it | 0.988 | 0.987 | 0.987 | 0.988 | 1.000 | 2025-07-24 | View |
| 3 | claude-3-5-haiku-20241022 | 0.988 | 0.987 | 0.987 | 0.988 | 1.000 | 2025-08-01 | View |
| 4 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.988 | 0.987 | 0.987 | 0.988 | 1.000 | 2025-07-29 | View |
| 5 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.975 | 0.974 | 0.975 | 0.975 | 1.000 | 2025-07-24 | View |
| 6 | gpt-4.1-nano | 0.975 | 0.974 | 0.975 | 0.975 | 1.000 | 2025-07-03 | View |
| 7 | gpt-4o-mini | 0.950 | 0.949 | 0.950 | 0.950 | 1.000 | 2025-07-02 | View |