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.
Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
Decides
choice, score, noul, classify, rank, route
choice, noul, score
Architecture
arc-decide
bekko
Fine-tuned from
qwen/qwen3-0.6b-base
cross-encoder/ettin-reranker-400m-v1
License
mit
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
5 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 arc-decide and bekko-system-one?
arc-decide is from Arc53 and bekko-system-one from Yuichi Tateno (hotchpotch). Both have open weights you can download and run. Both answer choice, score and noul questions. Only arc-decide answers classify, rank and route. bekko-system-one is the smaller model, at 395M parameters to 600M. arc-decide is licensed mit; bekko-system-one, other.
Which is more accurate, arc-decide or bekko-system-one?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, arc-decide or bekko-system-one?
arc-decide: Free (open weights). bekko-system-one: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or bekko-system-one locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull hotchpotch/bekko-system-one download the weights.
p95 latency
—
5.4 ms
Evaluation suite
—
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)