supply_chain_disclosure_best_practice_verification
- Task Description: Determine if a supply chain disclosure indicates engagement in verification and auditing practices or assessment of supplier risks.
- Task Type: Binary classification
- Document Type: corporate disclosure
- Number of Samples: 387
- Input Length Range: 107-5764 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 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.755 | 0.729 | 0.731 | 0.755 | 1.000 | 2025-07-25 | View |
| 2 | gpt-4o-mini | 0.715 | 0.697 | 0.699 | 0.715 | 1.000 | 2025-07-02 | View |
| 3 | claude-3-5-haiku-20241022 | 0.699 | 0.673 | 0.671 | 0.699 | 1.000 | 2025-08-01 | View |
| 4 | gpt-4.1-nano | 0.691 | 0.705 | 0.691 | 0.691 | 1.000 | 2025-07-03 | View |
| 5 | google/gemma-2-27b-it | 0.686 | 0.665 | 0.664 | 0.686 | 1.000 | 2025-07-24 | View |
| 6 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.670 | 0.626 | 0.594 | 0.670 | 1.000 | 2025-08-04 | View |
| 7 | claude-3-haiku-20240307 | 0.636 | 0.587 | 0.534 | 0.636 | 1.000 | 2025-07-25 | View |