Qwen Decision 27B noncausal LoRA vs Cloudflare clef
Qwen Decision 27B noncausal LoRA is more accurate on the Jev Decision Index, Cloudflare clef is better calibrated. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Qwen Decision 27B noncausal LoRA | Cloudflare clef |
|---|---|---|
| Provider | jsaurabh | Cloudflare |
| Decision Index score | 58.5 | 53.1 |
| Calibration error (ECE) | 0.051 | 0.040 |
| Median latency (p50) | 127 ms | 102 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 28B | 28B |
| 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 Qwen Decision 27B noncausal LoRA or Cloudflare clef more accurate?
Qwen Decision 27B noncausal LoRA scores higher on the Jev Decision Index (58.5 vs 53.1).
Which is better calibrated, Qwen Decision 27B noncausal LoRA or Cloudflare clef?
Cloudflare clef has the lower expected calibration error (0.040 vs 0.051), so its stated confidence is closer to how often it is right.
Is Qwen Decision 27B noncausal LoRA or Cloudflare clef 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.