Baseten: Mammoth 1 (free) vs frontier-infra Jebadiah 27B v2.1
Baseten: Mammoth 1 (free) and frontier-infra Jebadiah 27B v2.1 have no measured difference in accuracy, calibration or cost in our data yet.
| Spec | Baseten: Mammoth 1 (free) | frontier-infra Jebadiah 27B v2.1 |
|---|---|---|
| Provider | Baseten | Frontier Infra |
| Decision Index score | — | 64.4 |
| Calibration error (ECE) | — | 0.056 |
| Median latency (p50) | — | 303 ms |
| Cost per 1,000 decisions | Free | — |
| Parameters | — | 28B |
| Open weights | — | Yes |
| Question types | — | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | — | Decoder LM with a decision readout |
| License | — | apache-2.0 |
FAQ
Is Baseten: Mammoth 1 (free) or frontier-infra Jebadiah 27B v2.1 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, Baseten: Mammoth 1 (free) or frontier-infra Jebadiah 27B v2.1?
No calibration difference between Baseten: Mammoth 1 (free) and frontier-infra Jebadiah 27B v2.1 is recorded yet.
Is Baseten: Mammoth 1 (free) or frontier-infra Jebadiah 27B v2.1 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.