Best LLMs for query_validation autogenerated — DTP Benchmark
Models
Frontier on this task: Qwen 3.5 Flash at 8.63 / 10. Quality bar at 95%: 8.20.
point-estimate floor (CI low) · upper CI (less certain) · Bars sorted by blended cost; cheapest qualifier first. Greyed rows are MEDIUM+ models whose point estimate clears the bar but whose CI low does not.
Cost breakdown
| Model | Quality | Sample | Blended cost / call | Savings vs best | Mode |
|---|---|---|---|---|---|
| Qwen 3.5 Flash best Alibaba Cloud (DashScope) | 8.63 / 10 CI [8.33, 8.93] | n=100 · medium | $0.000169 | (anchor) | sync |
| Gemini 3 Flash Preview Gemini | 8.29 / 10 CI [8.05, 8.54] | n=100 · high | $0.001030 | — | batch |
Typical call shape for this task: 723 input tokens → 566 output tokens, EMA-tracked from production traffic. Blended cost = (in × in_price + out × out_price), rounded to 6 decimals.