deck31b (Gemma 4 31B) vs Cloudflare clef
deck31b (Gemma 4 31B) 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 | deck31b (Gemma 4 31B) | Cloudflare clef |
|---|---|---|
| Provider | krishna-gogineni-765 | Cloudflare |
| Decision Index score | 59.0 | 53.1 |
| Calibration error (ECE) | 0.204 | 0.040 |
| Median latency (p50) | 219 ms | 102 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 33B | 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 |
FAQ
Is deck31b (Gemma 4 31B) or Cloudflare clef more accurate?
deck31b (Gemma 4 31B) scores higher on the Jev Decision Index (59.0 vs 53.1).
Which is better calibrated, deck31b (Gemma 4 31B) or Cloudflare clef?
Cloudflare clef has the lower expected calibration error (0.040 vs 0.204), so its stated confidence is closer to how often it is right.
Is deck31b (Gemma 4 31B) 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.