Databricks says Genie Code beat three coding agents on 401 real tasks at $0.55 each
DbrxMosaicAI · x · 2026-07-25
- Databricks reports that adding context can improve both accuracy and cost for data agents.
- On 401 tasks distilled from internal usage, Genie Code was benchmarked against three leading general-purpose coding agents.
- Each agent used its own harness, frontier models, Databricks MCP, and the same 20-minute budget.
- Genie Code was the most accurate agent in the test at 76.6% and also the cheapest, with a mean cost of $0.55 per task.
- Databricks attributes the advantage to semantic search, persistent memory, and workspace understanding, which reduced inefficient exploration, errors, timeouts, and cost.
Related event: Databricks Claims Genie Code Beats Coding Agents at $0.55/Task(2 posts)→
More from coding & agent
- Mirendil debuts Fern, its first model with a 10M-token context window — shayan_ · 2026-10-27
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Prompt turns Claude Code into a forensics tool finding deleted iPhone photos in backups — alex_verem · 2026-10-27
- Phones won't be mobile IDEs but control planes for agent fleets, argues Yuchen Jin — Yuchenj_UW · 2026-10-27
- FrontierCS 2 launches on Kaggle: 48 tasks make agents beat published CS papers — MeganRisdal · 2026-10-27