Pydantic's Code Mode report: 51% faster long tasks across 8 models and 5,276 runs
samuelcolvin · x · 2026-10-29
Pydantic published a report on Code Mode / Programmatic Tool Calling / RLM: instead of a model writing out 200 tool calls to update 200 records and reading back each result, it writes one Python loop. Across 8 models and 5,276 runs, long tasks ran 51% faster and succeeded 16 points more often.
Related event: Pydantic's Code Mode Cuts Agent Tokens 30%, Speeds Tasks 51%(2 posts)→
More from coding & agent
- Grok voice agent breaks down, sparking rant against renting other people's agent harnesses — alexcovo_eth · 2026-10-29
- A silent skip counted as success: rebuilding a bot lane that can't go quiet unnoticed — petrusenko_max · 2026-10-29
- Independent dev: 'I just talk to Claude and the feature gets implemented' — evielync · 2026-10-29
- Dev argues subagent fleets are pointless with Claude Opus 5.5 — one-on-one prompting wins — ryunuck · 2026-10-29
- The "Brain Sandwich": a three-step workflow for using AI without atrophying your engineering judgment — bibryam · 2026-10-29
- Nolan Lawson benchmarks the AI cost of JS frameworks: results mostly similar — hichaelmart · 2026-10-29