insurance_policy_interpretation
- Task Description: Given an insurance claim and policy, determine whether the claim is covered by the policy.
- Task Type: 3-way classification
- Document Type: legal text
- Number of Samples: 138
- Input Length Range: 36-128 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: insurance 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-3-5-haiku-20241022 | 0.556 | 0.631 | 0.526 | 0.556 | 1.000 | 2025-08-01 | View |
| 2 | gpt-4.1-nano | 0.474 | 0.407 | 0.405 | 0.474 | 1.000 | 2025-07-03 | View |
| 3 | gpt-4o-mini | 0.451 | 0.557 | 0.392 | 0.451 | 1.000 | 2025-07-02 | View |
| 4 | google/gemma-2-27b-it | 0.436 | 0.448 | 0.354 | 0.436 | 1.000 | 2025-07-24 | View |
| 5 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.429 | 0.515 | 0.361 | 0.429 | 1.000 | 2025-07-25 | View |
| 6 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.421 | 0.444 | 0.320 | 0.421 | 1.000 | 2025-07-30 | View |
| 7 | claude-3-haiku-20240307 | 0.323 | 0.352 | 0.251 | 0.323 | 1.000 | 2025-07-25 | View |