Cloudflare clef vs Jobe
Cloudflare clef 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 | Cloudflare clef | Jobe |
|---|---|---|
| Provider | Cloudflare | MantisShrimpdev |
| Decision Index score | 53.1 | 33.1 |
| Calibration error (ECE) | 0.040 | 0.123 |
| Median latency (p50) | 102 ms | 54 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 28B | 5B |
| 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 Cloudflare clef or Jobe more accurate?
Cloudflare clef scores higher on the Jev Decision Index (53.1 vs 33.1).
Which is better calibrated, Cloudflare clef or Jobe?
Cloudflare clef has the lower expected calibration error (0.040 vs 0.123), so its stated confidence is closer to how often it is right.
Is Cloudflare clef or Jobe 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.