Accounting

Sansa Bench

Accounting leaderboard for Sansa Bench, with charts, model comparison, and methodology. This dimension covers accounting principles, financial reporting standards, and practice topics such as revenue recognition and depreciation.

Inspiration & Acknowledgments91 models testedUpdated Aug 8, 2026

Top models for Accounting

  1. 1.Claude-Opus-4.8 Reasoning High0.811
  2. 2.Claude-Opus-5 Reasoning High0.804
  3. 3.Claude-Sonnet-4.5 Reasoning None0.709
  4. 4.Claude-Sonnet-4.6 Reasoning None0.708
  5. 5.Deepseek-V4-Flash Reasoning High0.706

Methodology: Accounting

What it measures

Tests knowledge and understanding of accounting principles, financial reporting standards (e.g., US GAAP, IFRS), and accounting practices. Queries cover topics such as revenue recognition, lease accounting, depreciation, financial statement preparation, and regulatory compliance.

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:
A company purchases office supplies for $500 cash. What is the effect on the accounting equation?
 
A. Assets increase by $500, liabilities increase by $500
B. Assets decrease by $500, expenses increase by $500
C. Assets increase by $500, equity increases by $500
D. Assets decrease by $500, equity decreases by $500
Answer:
D