Cloudflare clef vs garas (Gemma 4 31B)
garas (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 | Cloudflare clef | garas (Gemma 4 31B) |
|---|---|---|
| Provider | Cloudflare | plantwaterer |
| Decision Index score | 53.1 | 58.3 |
| Calibration error (ECE) | 0.040 | 0.049 |
| Median latency (p50) | 102 ms | 117 ms |
| Cost per 1,000 decisions | — | — |
| Parameters | 28B | 31B |
| 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 Cloudflare clef or garas (Gemma 4 31B) more accurate?
garas (Gemma 4 31B) scores higher on the Jev Decision Index (58.3 vs 53.1).
Which is better calibrated, Cloudflare clef or garas (Gemma 4 31B)?
Cloudflare clef has the lower expected calibration error (0.040 vs 0.049), so its stated confidence is closer to how often it is right.
Is Cloudflare clef or garas (Gemma 4 31B) 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.