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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
open-jev
state-decider
Fine-tuned from
microsoft/deberta-v3-large
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
85.4%
76.8%
Calibration error
0.022
—
Valid action rate
—
—
Median latency
28 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.
Questions
What is the difference between open-jev-deberta-v3-large and state-decider-1?
open-jev-deberta-v3-large is from Kotoba Labs and state-decider-1 from meraGPT. open-jev-deberta-v3-large has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul and classify questions. Only state-decider-1 answers route. state-decider-1 reads up to 4K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, open-jev-deberta-v3-large or state-decider-1?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or state-decider-1?
open-jev-deberta-v3-large: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run open-jev-deberta-v3-large or state-decider-1 locally?
open-jev-deberta-v3-large yes — systemone pull kotoba-labs/open-jev-deberta-v3-large downloads its weights. The other is only served as a hosted API.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
