Perplexity Decider v1.1 (27B) vs Darwin-27B-ZTC
Perplexity Decider v1.1 (27B) is more accurate on the Jev Decision Index, Darwin-27B-ZTC is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Perplexity Decider v1.1 (27B) | Darwin-27B-ZTC |
|---|---|---|
| Provider | Perplexity | FINAL_Bench |
| Decision Index score | 62.8 | 62.5 |
| Calibration error (ECE) | 0.071 | 0.045 |
| Median latency (p50) | 104 ms | 104 ms |
| Cost per 1,000 decisions | $0.0040 | — |
| Parameters | 28B | 26B |
| Open weights | Yes | Yes |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | Decoder LM with a decision readout | Decoder LM with a decision readout |
| License | apache-2.0 | apache-2.0 |
FAQ
Is Perplexity Decider v1.1 (27B) or Darwin-27B-ZTC more accurate?
Perplexity Decider v1.1 (27B) scores higher on the Jev Decision Index (62.8 vs 62.5).
Which is better calibrated, Perplexity Decider v1.1 (27B) or Darwin-27B-ZTC?
Darwin-27B-ZTC has the lower expected calibration error (0.045 vs 0.071), so its stated confidence is closer to how often it is right.
Is Perplexity Decider v1.1 (27B) or Darwin-27B-ZTC cheaper per 1,000 decisions?
A hosted price is not recorded for both models; open-weight models cost the compute you run them on.
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.