Sansa Bench
Security studies leaderboard for Sansa Bench, with charts, model comparison, and methodology. This dimension covers cybersecurity, information security, security policy, and related security concepts.
Top models for Security Studies
- 1.
Claude-Opus-5 Reasoning High0.907 - 2.
Gpt-5.4 Reasoning High0.813 - 3.
Glm-5.2 Reasoning High0.801 - 4.Gpt-5.4 Reasoning Low0.792
- 5.
Gemini-3.1-Pro-Preview Reasoning High0.785
Methodology: Security Studies
What it measures
Tests security studies knowledge and understanding, including cybersecurity, information security, security policies, and security practices. Queries evaluate understanding of security concepts.
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.