HEAD TO HEAD
FrontiersMind: lumma-fev and Kotoba Labs: open-jev-deberta-v3-large, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | frontiersmind/lumma-fev | kotoba-labs/open-jev-deberta-v3-large |
|---|---|---|
| Summary | FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated. | An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only. |
| Decides | choice, score, noul | choice, score, noul, classify |
| Architecture | lumma-fev | open-jev |
| Fine-tuned from | frontiersmind/lumma-0.6b-base | microsoft/deberta-v3-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 64.0% | 85.4% |
| Calibration error | — | 0.022 |
| Valid action rate | — | — |
| Median latency | 45.8 ms | 28 ms |
| p95 latency | — | — |
| Evaluation suite | typed-decisions (maker's table; split not stated) | Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) |
| Latest version | 2026.09 | 2026.09 |
| Variants | LICENSE, NOTICE | — |
| Size of latest version | 1.2 GB | 1.6 GB |
| Files | 12 | 9 |
| Downloads | 1 | 2 |
| Stars | 0 | 0 |
| Tags | system-one, pointer-head, multilingual, indic, 649m | system-one, encoder, deberta, public-data, 434m |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
lumma-fev is from FrontiersMind and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score and noul questions. Only open-jev-deberta-v3-large answers classify. lumma-fev reads up to 8K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 649M.
They report on different suites — lumma-fev 64.0% on typed-decisions (maker's table; split not stated), open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
lumma-fev: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and lumma-fev in about 45.8 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull frontiersmind/lumma-fev and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.