New: GPT-6.2 benchmark report is here.Read the report ↗

Best LLMs on AA-AnalystAgent

AA-AnalystAgent

Professional spreadsheet and report analysis from Artificial Analysis.

Updated: Data as of:
Limited reportingNot saturated
Official benchmark
AA-AnalystAgent results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
GPT-6.2 AstraOpenAI · ProprietaryOpenAI GPT-6.2 launch / five independent attempts62.5%
View all 1 published reports
OpenAI GPT-6.2 launch / five independent attempts

attempts: 5 · metric interpretation: Questions answered correctly on all five independent attempts

OpenAI ↗