We don't claim to be "good" in the abstract. We take the same model, answering the same database question, two ways: with SIXTA available and without it. The difference is what SIXTA adds. We run the whole suite several times and report the average, because a single model run is noisy.
The assistant answers from its own knowledge. The baseline.
Same model, same question, with the SIXTA tools available.
The deterministic tool output, no model. The ground reference.
129 cases across MySQL and PostgreSQL and all 13 tools, graded blind (our branding stripped) by a majority vote of three independent models. Each metric is computed per run; we report the mean and its range. The connected arm holds steady run to run; the model-alone baseline bounces, so we average it and show the spread rather than cite one run.
SIXTA runs with frontier models, not against them. A general model knows databases; it doesn't know the lock behaviour of your engine version or, on Pro, the state of your database. The model brings the language, SIXTA brings the database judgment, and the numbers below measure what that judgment adds.
| Model | Critical-issue recall | Unsafe migrations approved | Flatly wrong answers |
|---|---|---|---|
| Small tier | 75% → 97% | ~7% → 0% | ~14 → ~1 |
| Mid tier | 90% → 100% | ~5% → 0% | ~4 → 0 |
| Frontier tier | 94% → 100% | ~5% → 0% | ~5 → 0 |
The tiers are current production models from a frontier lab, small to frontier; we re-run the suite as models update. Small models gain the most from connecting: SIXTA cuts their wrong answers from ~14 to about 1 (the hardest version-specific cases still slip occasionally). On the recommended mid and frontier tiers, connected answers are flatly wrong zero times, every run. Connected safety is stable across every run and every tier: 0% unsafe migrations was 0 of 75 trial runs. "Unsafe migrations approved" = the model called a table-locking or data-rewriting migration safe, the most consequential error.
No connection to set up. The free Connect tier works only from the SQL you paste: no credentials, no access to your systems. Connecting to your live database is the paid Connect Pro tier (on demand) or the SIXTA platform (continuous).
Nothing stored. Pasted SQL is analyzed in memory and never persisted.
Deterministic verdicts. Same artifact, same analysis, from version-aware rules. The model relays them, it doesn't invent them.
Self-checked fixes. Every rewrite is re-analyzed before you see it, and flagged if it isn't clean.
129 cases · MySQL & PostgreSQL · 3-model blind judge panel · averaged over repeated runs · last updated 20 Jun 2026. Architectural items above are guarantees; the figures are measured results on our own suite, not absolute guarantees for every possible input.