Loading comparison…
HEAD TO HEAD
akhilaaa3: jev-omni and Interfaze AI: lev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | akhilaaa3/jev-omni | interfaze-ai/lev |
|---|---|---|
| Summary | A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing. | An open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API. |
| Decides | choice, noul, score, classify | choice, score, noul, classify, route |
| Architecture | jev-omni | lev |
| Fine-tuned from | google/gemma-4-12b-it | qwen/qwen3.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.6% | 68.9% |
| Calibration error | 0.040 | 0.115 |
| Valid action rate | — | — |
| Median latency | 83 ms | 69 ms |
| p95 latency | — | — |
| Evaluation suite | DecisionBench Medium (author's set) | S1Bench (13 public subsets, macro) |
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.
jev-omni is from akhilaaa3 and lev from Interfaze AI. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. Only lev answers route. lev is the smaller model, at 4.0B parameters to 12B.
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), lev 68.9% on S1Bench (13 public subsets, macro) — so the numbers do not rank them. Test both on your own labelled examples.
jev-omni: Free (open weights). lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, lev answers in about 69 ms at the median and jev-omni in about 83 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull interfaze-ai/lev download the weights.
| Latest version | 2026.09 | 2026.09 |
|---|
| Variants | unified | — |
|---|
| Size of latest version | 22.3 GB | 195.1 MB |
|---|
| Files | 6 | 8 |
|---|
| Downloads | 0 | 0 |
|---|
| Stars | 0 | 0 |
|---|
| Tags | system-one, multimodal, gemma, vision, audio, 12b | system-one, qwen, lora, calibrated, 4b |
|---|
| Updated | Sep 27, 2026 | Sep 27, 2026 |
|---|