Leaderboard

AA-AnalystAgent

Agents work through folders of spreadsheets and documents to answer quantitative questions that business and data analysts face. The emphasis is on judgement and method. It spans 14 business and scientific domains and is not finance-specific.

Best reported

60

Gemini 3.7 Flash (High)Google

pass^5 %

date not stated

AA-AnalystAgent

pass^5 %, higher is better. 3 models.

Updated date not stated

  1. Gemini 3.7 Flash (High)60
  2. Claude Fable 5.1 (Max, Default Fallback)57.5
  3. Claude Sonnet 5.5 (Max, Default Fallback)57.5

AA-AnalystAgent

pass^5 %, higher is better. 3 models.

Updated date not stated

  1. 1Gemini 3.7 Flash (High)60
  2. 2Claude Fable 5.1 (Max, Default Fallback)57.5
  3. 2Claude Sonnet 5.5 (Max, Default Fallback)57.5
AA-AnalystAgent leaderboard (pass^5 %, higher is better)
1Gemini 3.7 Flash (High)Google60Stirrup harnessArtificial Analysis evaluation page
Official board, date not stated
2Claude Fable 5.1 (Max, Default Fallback)Anthropic57.5Stirrup harnessArtificial Analysis evaluation page
Official board, date not stated
2Claude Sonnet 5.5 (Max, Default Fallback)Anthropic57.5Stirrup harnessArtificial Analysis evaluation page
Official board, date not stated

Full details for AA-AnalystAgent