abercrombie
- Task Description: Determine the Abercrombie classification for a mark/product pair.
- Task Type: 5-way classification
- Document Type: legal question
- Number of Samples: 100
- Input Length Range: 9-28 tokens
- Evaluation Metrics: accuracy (maximize), balanced_accuracy (maximize), f1_macro (maximize), f1_micro (maximize), valid_predictions_ratio (maximize)
- Tags: rule application, trademark law
- Paper: LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Dataset Download: https://hazyresearch.stanford.edu/legalbench/
19 submissions
| Rank | Model | accuracy | balanced_accuracy | f1_macro | f1_micro | valid_predictions_ratio | Date | Results |
|---|---|---|---|---|---|---|---|---|
| 1 | claude-opus-4-20250514 | 0.895 | 0.895 | 0.896 | 0.895 | 1.000 | 2025-07-25 | View |
| 2 | claude-opus-4-1-20250805 | 0.874 | 0.874 | 0.870 | 0.874 | 1.000 | 2025-08-05 | View |
| 3 | o4-mini | 0.863 | 0.863 | 0.856 | 0.863 | 1.000 | 2025-07-08 | View |
| 4 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 0.842 | 0.842 | 0.843 | 0.842 | 1.000 | 2025-07-28 | View |
| 5 | gpt-5-2025-08-07 | 0.842 | 0.842 | 0.839 | 0.842 | 1.000 | 2025-08-07 | View |
| 6 | grok-4-0709 | 0.842 | 0.842 | 0.842 | 0.842 | 1.000 | 2025-07-29 | View |
| 7 | grok-3-mini | 0.842 | 0.842 | 0.834 | 0.842 | 1.000 | 2025-07-28 | View |
| 8 | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 0.821 | 0.821 | 0.817 | 0.821 | 1.000 | 2025-07-24 | View |
| 9 | o3 | 0.821 | 0.821 | 0.817 | 0.821 | 1.000 | 2025-07-08 | View |
| 10 | deepseek-ai/DeepSeek-V3 | 0.811 | 0.811 | 0.801 | 0.811 | 1.000 | 2025-07-11 | View |
| 11 | openai/gpt-oss-120b | 0.811 | 0.811 | 0.814 | 0.811 | 1.000 | 2025-08-05 | View |
| 12 | claude-sonnet-4-20250514 | 0.779 | 0.779 | 0.777 | 0.779 | 1.000 | 2025-07-25 | View |
| 13 | gpt-4o-mini | 0.747 | 0.747 | 0.746 | 0.747 | 1.000 | 2025-07-02 | View |
| 14 | o3-mini | 0.737 | 0.737 | 0.692 | 0.737 | 1.000 | 2025-07-09 | View |
| 15 | claude-3-5-haiku-20241022 | 0.726 | 0.726 | 0.695 | 0.726 | 1.000 | 2025-08-01 | View |
| 16 | google/gemma-2-27b-it | 0.632 | 0.632 | 0.636 | 0.632 | 1.000 | 2025-07-24 | View |
| 17 | gpt-4.1-nano | 0.621 | 0.621 | 0.602 | 0.621 | 1.000 | 2025-07-03 | View |
| 18 | claude-3-haiku-20240307 | 0.611 | 0.611 | 0.615 | 0.611 | 1.000 | 2025-07-24 | View |
| 19 | deepseek-ai/DeepSeek-R1 | 0.583 | 0.635 | 0.587 | 0.583 | 0.878 | 2025-07-11 | View |