Psychology

Sansa Bench

Psychology leaderboard for Sansa Bench, with charts, model comparison, and methodology. This dimension covers cognitive and behavioral psychology, theories, and psychological processes.

Inspiration & Acknowledgments91 models testedUpdated Aug 8, 2026

Top models for Psychology

  1. 1.Gemini-3-Pro-Preview Reasoning High0.912
  2. 2.Gemini-3.1-Pro-Preview Reasoning High0.792
  3. 3.Claude-Sonnet-4.6 Reasoning Low0.713
  4. 4.Claude-Sonnet-4.5 Reasoning Low0.705
  5. 5.Gpt-5.4 Reasoning High0.704

Methodology: Psychology

What it measures

Tests psychology knowledge and understanding, including cognitive psychology, behavioral psychology, psychological theories, and psychological processes. Queries evaluate understanding of human psychology.

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.

Example Question

Question:
In classical conditioning, what term describes the phenomenon where a Conditioned Response (CR) reappears after a period of rest following Extinction?
 
A. Generalization
B. Spontaneous Recovery
C. Discrimination
D. Higher-order conditioning
Answer:
B