Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
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, route
choice, score, noul, classify
Architecture
intern-decision
open-jev
Fine-tuned from
qwen/qwen3.5-4b
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.6%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
44 ms
28 ms
p95 latency
44.6 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 intern-decision and open-jev-deberta-v3-large?
intern-decision is from InternLM (Shanghai AI Laboratory) 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 intern-decision answers route. intern-decision 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 4.5B.
Which is more accurate, intern-decision or open-jev-deberta-v3-large?
They report on different suites — intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), 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.
Which is cheaper, intern-decision or open-jev-deberta-v3-large?
intern-decision: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, intern-decision or open-jev-deberta-v3-large?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and intern-decision in about 44 ms — measured on different hardware, so treat it as a rough guide.
Can I run intern-decision or open-jev-deberta-v3-large locally?
Yes, both: systemone pull internlm/intern-decision and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
