Best LLMs for synthesis_analysis autogenerated — DTP Benchmark
Models
Frontier on this task: Claude Sonnet 4.6 at 8.95 / 10. Quality bar at 95%: 8.50.
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 3.6 Plus Alibaba Cloud (DashScope) | 8.79 / 10 CI [8.69, 8.90] | n=40 · ranked | $0.014724 | 77% cheaper | sync |
| Claude Sonnet 4.6 best Anthropic | 8.95 / 10 CI [8.74, 9.15] | n=29 · high | $0.065295 | (anchor) | batch |
| Claude Opus 4.7 Anthropic | 8.77 / 10 CI [8.51, 9.04] | n=25 · high | $0.108825 | — | batch |
Typical call shape for this task: 34660 input tokens → 1774 output tokens, EMA-tracked from production traffic. Blended cost = (in × in_price + out × out_price), rounded to 6 decimals.