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.
Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
open-jev
standard-one
Fine-tuned from
microsoft/deberta-v3-large
mistralai/ministral-3-8b-instruct-2512-bf16
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Standard Thinking
Input price
—
—
Decision accuracy
85.4%
71.1%
Calibration error
0.022
—
Valid action rate
—
—
Median latency
28 ms
25.8 ms
p95 latency
—
41.9 ms
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.
Questions
What is the difference between open-jev-deberta-v3-large and standard-one?
open-jev-deberta-v3-large is from Kotoba Labs and standard-one from Standard Thinking. open-jev-deberta-v3-large has open weights you can download and run; standard-one has open weights and a hosted API. Both answer choice, score, noul and classify questions. Only standard-one answers route. standard-one 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 8.0B.
Which is more accurate, open-jev-deberta-v3-large or standard-one?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or standard-one?
open-jev-deberta-v3-large: Free (open weights). standard-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Which is faster, open-jev-deberta-v3-large or standard-one?
By their publishers’ figures, standard-one answers in about 25.8 ms at the median and open-jev-deberta-v3-large in about 28 ms — measured on different hardware, so treat it as a rough guide.
Can I run open-jev-deberta-v3-large or standard-one locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull standard-thinking/standard-one download the weights.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
