Tev1-4B-experimental vs ScaleDown Classify-1
ScaleDown Classify-1 is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Tev1-4B-experimental | ScaleDown Classify-1 |
|---|---|---|
| Provider | Together | ScaleDown |
| Decision Index score | 34.1 | — |
| Calibration error (ECE) | 0.104 | — |
| Median latency (p50) | 36 ms | — |
| Cost per 1,000 decisions | $0.0084 | $0.0080 |
| Parameters | 5B | — |
| 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 | Encoder classifier |
| License | — | proprietary |
FAQ
Is Tev1-4B-experimental or ScaleDown Classify-1 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, Tev1-4B-experimental or ScaleDown Classify-1?
No calibration difference between Tev1-4B-experimental and ScaleDown Classify-1 is recorded yet.
Is Tev1-4B-experimental or ScaleDown Classify-1 cheaper per 1,000 decisions?
ScaleDown Classify-1 is cheaper: about $0.0080 vs $0.0084 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.