consumer_contracts_qa
- Task Description: Answer yes/no questions on the rights and obligations created by clauses in terms of services agreements.
- Task Type: Yes/No question-answer
- Document Type: contract clause
- Number of Samples: 400
- Input Length Range: 7-51 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 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.977 | 0.978 | 0.977 | 0.977 | 1.000 | 2025-07-28 | View |
2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.975 | 0.974 | 0.974 | 0.975 | 1.000 | 2025-07-24 | View |
3 | google/gemma-2-27b-it | 0.960 | 0.961 | 0.959 | 0.960 | 1.000 | 2025-07-24 | View |
4 | claude-3-5-haiku-20241022 | 0.942 | 0.940 | 0.941 | 0.942 | 1.000 | 2025-08-01 | View |
5 | gpt-4o-mini | 0.922 | 0.923 | 0.921 | 0.922 | 1.000 | 2025-07-02 | View |
6 | claude-3-haiku-20240307 | 0.907 | 0.906 | 0.906 | 0.907 | 1.000 | 2025-07-25 | View |
7 | gpt-4.1-nano | 0.884 | 0.879 | 0.881 | 0.884 | 1.000 | 2025-07-03 | View |