Loading comparison…
HEAD TO HEAD
Frontier Infra: jebadiah and AutoTrust AI Lab: jev-27b, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | frontier-infra/jebadiah | autotrust-ai/jev-27b |
|---|---|---|
| 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. | AutoTrust's student of TypeSafe Jev 1.13. A frozen Qwen3.8-27B plus a 108.9M-parameter decision block trained on Jev's own output distributions; one set of weights answers typed questions in one pass (System 1) or generates text with the untouched base (System 2). |
| Decides | choice, score, noul, classify, route | choice, score, noul |
| Architecture | jebadiah | blocks-of-experts |
| Fine-tuned from | qwen/qwen3.8-27b | qwen/qwen3.8-27b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 86.6% | 88.7% |
| Calibration error | 0.113 | — |
| Valid action rate | — | — |
| Median latency | — | 137 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 jev-27b from AutoTrust AI Lab. Both have open weights you can download and run. Both answer choice, score and noul questions. Only jebadiah answers classify and route.
They report on different suites — jebadiah 86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier, jev-27b 88.7% on JevBench public set (231 items), family-macro score, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
jebadiah: Free (open weights). jev-27b: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull frontier-infra/jebadiah and systemone pull autotrust-ai/jev-27b download the weights.
| Evaluation suite |
|---|
| JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier |
| JevBench public set (231 items), family-macro score, maker's run |
| Latest version | 2026.09 | 2026.09 |
|---|
| Variants | eval, LICENSE, scripts | adapter_vllm, adapter, reports |
|---|
| Size of latest version | 51.8 GB | 50.9 GB |
|---|
| Files | 63 | 42 |
|---|
| Downloads | 0 | 0 |
|---|
| Stars | 0 | 0 |
|---|
| Tags | system-one, qwen, lora, jevbench, gguf, mlx, 27b | system-one, qwen, distillation, vllm, dual-head, 27b |
|---|
| Updated | Sep 30, 2026 | Sep 30, 2026 |
|---|