Sansa Bench
Law leaderboard for Sansa Bench, with charts, model comparison, and methodology. This dimension covers legal principles, case analysis, legal reasoning, and legal systems.
Top models for Law
- 1.
Claude-Sonnet-4.5 Reasoning High1.000
- 2.
Claude-Sonnet-4.6 Reasoning Low1.000
- 3.
Claude-Sonnet-4.6 Reasoning High1.000
- 4.
Claude-Opus-5 Reasoning High1.000
- 5.
Claude-Sonnet-4.5 Reasoning Low0.999
Methodology: Law
What it measures
Tests legal knowledge and understanding, including legal principles, case law, legal reasoning, and legal systems. Queries evaluate understanding of legal concepts and their applications.
Scoring & Criteria
Returns score 1.0 if the extracted answer exactly matches the expected answer letter (after normalization), otherwise 0.0. The system prompt requests answers in `<answer>X</answer>` format where X is a letter from the provided choices (A, B, C, D, etc.). The grader normalizes for models that include the full choice text instead of just the letter, or that violate the answer tag format from the system prompt. Only one answer is correct.
Evaluation Type: Multiple Choice
Grades multiple choice responses by exact string matching with normalization.