A 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks.
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, classify, rank, route
choice, score, noul, classify
Architecture
arc-decide
open-jev
Fine-tuned from
qwen/qwen3-0.6b-base
microsoft/deberta-v3-large
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
85.4%
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 arc-decide and open-jev-deberta-v3-large?
arc-decide is from Arc53 and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only arc-decide answers rank and route. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 600M. arc-decide is licensed mit; open-jev-deberta-v3-large, apache-2.0.
Which is more accurate, arc-decide or open-jev-deberta-v3-large?
Only open-jev-deberta-v3-large publishes an accuracy figure (85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or open-jev-deberta-v3-large?
arc-decide: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or open-jev-deberta-v3-large locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
—
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
