# Julius AI

Julius AI publishes no per-task cost or token figure in the AgentBurn index. AgentBurn snapshot 2026-10-27. Every figure carries a provenance label: source-backed, derived, or left empty when no public basis exists.

| Metric | Value | Basis |
|---|---|---|
| Tokens per task | not published | not_public |
| Cost per task | not published | not_public |
| Success rate | not published | not_public |
| Cost per solved task | not published | — |
| Runs per day (estimate) | 68,000 | model |

Data analyst agent that runs real Python on your spreadsheet

Julius takes a dataset or spreadsheet, inspects the schema, writes and executes Python for the analysis, and returns charts plus a written interpretation. Because the code actually runs in a sandbox, the agent can iterate on failed cells and export a reproducible notebook instead of guessing at numbers.

Data snapshot: 2026-10-27 · https://getagentburn.com/projects/julius/