A model update just shipped.
Do you know what it broke?

Model updates don't just improve — they redistribute capability. Some tasks get better; adjacent ones silently regress. Model-Drift Watch runs a fixed battery of production-shaped regression tasks against every major release, across providers, and publishes the diff — so you find out the same day, not from your customers.

Sample release diff — illustrative format, real data ships with scorecard #1

Workflow archetypePreviousNew releaseFlip rateVerdict
Structured output (JSON)5/55/50/5stable
Tool/function calling5/52/53/5regression
Long-doc extraction4/55/51/5improved
Instruction adherence5/54/51/5watch

Illustrative sample. Methodology: N=5 trials per task, temperature 0, deterministic checkers. A regression = ≥3/5 failures on a task that previously passed ≥4/5. Task categories are published; raw task inputs never are.

  1. Every major release (~8–12/year across providers) we run the full battery within hours.
  2. Free scorecard published for every release — what changed, by archetype.
  3. Paid tier maps the diff to your workflow archetypes with patch recommendations, same day.

Get the next release diff, same day

Free forever for the public scorecard. No spam; one email per model release.