international_citizenship_questions
- Task Description: Answer questions about citizenship law from across the world.
- Task Type: Binary classification
- Document Type: legal question
- Number of Samples: 9310
- Input Length Range: 20-75 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: international law, legal knowledge
- 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 | 0.605 | 0.633 | 0.602 | 0.605 | 1.000 | 2025-08-01 | View |
| 2 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.552 | 0.600 | 0.530 | 0.552 | 1.000 | 2025-07-25 | View |
| 3 | claude-3-haiku-20240307 | 0.548 | 0.567 | 0.547 | 0.548 | 1.000 | 2025-07-25 | View |
| 4 | gpt-4.1-nano | 0.533 | 0.561 | 0.529 | 0.533 | 1.000 | 2025-07-03 | View |
| 5 | google/gemma-2-27b-it | 0.489 | 0.552 | 0.435 | 0.489 | 1.000 | 2025-07-24 | View |
| 6 | gpt-4o-mini | 0.482 | 0.537 | 0.440 | 0.482 | 1.000 | 2025-07-02 | View |
| 7 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.460 | 0.528 | 0.387 | 0.460 | 1.000 | 2025-07-31 | View |