learned_hands_torts
- Task Description: Classify if a user post implicates legal issues related to torts.
- Task Type: Binary classification
- Document Type: legal question
- Number of Samples: 438
- Input Length Range: 18-3444 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: issue spotting, tort law
- 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 | 0.620 | 0.620 | 0.583 | 0.620 | 1.000 | 2025-08-03 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.595 | 0.595 | 0.558 | 0.595 | 1.000 | 2025-07-25 | View |
| 3 | google/gemma-2-27b-it | 0.579 | 0.579 | 0.502 | 0.579 | 1.000 | 2025-07-24 | View |
| 4 | claude-3-5-haiku-20241022 | 0.574 | 0.574 | 0.500 | 0.574 | 1.000 | 2025-08-01 | View |
| 5 | gpt-4.1-nano | 0.539 | 0.539 | 0.533 | 0.539 | 1.000 | 2025-07-03 | View |
| 6 | claude-3-haiku-20240307 | 0.536 | 0.535 | 0.437 | 0.536 | 0.993 | 2025-07-25 | View |
| 7 | gpt-4o-mini | 0.528 | 0.528 | 0.396 | 0.528 | 1.000 | 2025-07-02 | View |