SimpleJev Qwen3.6-35B-A3B (Featherless) vs Celeris-1 Decision
SimpleJev Qwen3.6-35B-A3B (Featherless) is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | SimpleJev Qwen3.6-35B-A3B (Featherless) | Celeris-1 Decision |
|---|---|---|
| Provider | Featherless AI | Celeris |
| Decision Index score | — | — |
| Calibration error (ECE) | — | — |
| Median latency (p50) | — | — |
| Cost per 1,000 decisions | Free | $0.0080 |
| Parameters | — | — |
| Open weights | Yes | No |
| 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 | Diffusion LM |
| License | Apache-2.0 (code) | proprietary |
FAQ
Is SimpleJev Qwen3.6-35B-A3B (Featherless) or Celeris-1 Decision more accurate?
At least one of the two has no Jev Decision Index score yet, so their accuracy cannot be compared here.
Which is better calibrated, SimpleJev Qwen3.6-35B-A3B (Featherless) or Celeris-1 Decision?
No calibration difference between SimpleJev Qwen3.6-35B-A3B (Featherless) and Celeris-1 Decision is recorded yet.
Is SimpleJev Qwen3.6-35B-A3B (Featherless) or Celeris-1 Decision cheaper per 1,000 decisions?
SimpleJev Qwen3.6-35B-A3B (Featherless) is cheaper: about Free vs $0.0080 per 1,000 decisions at 200 input tokens each.
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.