ScaleDown Classify-1 vs Perplexity Decider v1.1 (27B)
Perplexity Decider v1.1 (27B) is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | ScaleDown Classify-1 | Perplexity Decider v1.1 (27B) |
|---|---|---|
| Provider | ScaleDown | Perplexity |
| Decision Index score | — | 62.8 |
| Calibration error (ECE) | — | 0.071 |
| Median latency (p50) | — | 104 ms |
| Cost per 1,000 decisions | $0.0080 | $0.0040 |
| Parameters | — | 28B |
| Open weights | No | Yes |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | Encoder classifier | Decoder LM with a decision readout |
| License | proprietary | apache-2.0 |
FAQ
Is ScaleDown Classify-1 or Perplexity Decider v1.1 (27B) more accurate?
At least one of the two has no Jev Decision Index score yet, so their accuracy cannot be compared here.
Which is better calibrated, ScaleDown Classify-1 or Perplexity Decider v1.1 (27B)?
No calibration difference between ScaleDown Classify-1 and Perplexity Decider v1.1 (27B) is recorded yet.
Is ScaleDown Classify-1 or Perplexity Decider v1.1 (27B) cheaper per 1,000 decisions?
Perplexity Decider v1.1 (27B) is cheaper: about $0.0040 vs $0.0080 per 1,000 decisions at 200 input tokens each.
Cost per 1,000 decisions assumes 200 input tokens per decision. Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.