Our data-analyst agent lost to a single prompt: 0.55 vs 0.70 on DABench with a 1.5B model
We built a data-analyst agent : it reads a question about a CSV file, plans the analysis, writes pandas code, runs it in a sandbox, reads the error if something breaks, and repairs its own code. It is the kind of loop most agent tutorials recommend. Then we compared it with the simplest possible ba…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-18 15:36 · DEV Community — AI
Our data-analyst agent lost to a single prompt: 0.55 vs 0.70 on DABench with a 1.5B model