Best LLMs for sec-s1-chunk-analysis autogenerated — DTP Benchmark
Models
Frontier on this task: GPT-5.5 at 8.84 / 10. Quality bar at 95%: 8.40.
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 |
|---|---|---|---|---|---|
| Kimi K2.6 Moonshot AI | 8.54 / 10 CI [8.39, 8.69] | n=100 · ranked | $0.020132 | 82% cheaper | batch |
| GPT-5.5 best OpenAI | 8.84 / 10 CI [8.74, 8.95] | n=84 · ranked | $0.112960 | (anchor) | batch |
Typical call shape for this task: 12106 input tokens → 5513 output tokens, EMA-tracked from production traffic. Blended cost = (in × in_price + out × out_price), rounded to 6 decimals.