Loading comparison…
HEAD TO HEAD
Frontier Infra: jebadiah and Convai Innovations: laya, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | frontier-infra/jebadiah | convai-innovations/laya |
|---|---|---|
| Summary | Frontier Infra's open decision model. A LoRA merged into Qwen3.8-27B (thinking off) that answers one typed question per forward pass with a probability over the option labels, served through AINode's TypeSafe-compatible /v1/systemone. | An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | jebadiah | laya |
| Fine-tuned from | qwen/qwen3.8-27b | answerdotai/modernbert-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 86.6% | — |
| Calibration error | 0.113 | — |
| Valid action rate | — | — |
| Median latency | — | 39.5 ms |
| p95 latency | — | — |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
jebadiah is from Frontier Infra and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. laya is the smaller model, at 421M parameters to 27B.
Only jebadiah publishes an accuracy figure (86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier); laya does not, so there is no comparison to make without your own test.
jebadiah: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull frontier-infra/jebadiah and systemone pull convai-innovations/laya download the weights.
| Evaluation suite | JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier | — |
|---|
| Latest version | 2026.09 | 2026.09.25 |
|---|
| Variants | eval, LICENSE, scripts | encoder, eval, multilingual, tokenizer, typed-decisions |
|---|
| Size of latest version | 51.8 GB | 2.2 GB |
|---|
| Files | 63 | 19 |
|---|
| Downloads | 0 | 1 |
|---|
| Stars | 0 | 0 |
|---|
| Tags | system-one, qwen, lora, jevbench, gguf, mlx, 27b | system-one, encoder, modernbert, rlcd, multilingual, 421m |
|---|
| Updated | Sep 30, 2026 | Sep 30, 2026 |
|---|