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.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
standard-one
winnow
Fine-tuned from
mistralai/ministral-3-8b-instruct-2512-bf16
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Standard Thinking
—
Input price
—
—
Decision accuracy
71.1%
85.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
25.8 ms
143 ms
p95 latency
41.9 ms
—
Evaluation suite
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 standard-one and winnow?
standard-one is from Standard Thinking and winnow from EldanRing. standard-one has open weights and a hosted API; winnow has open weights you can download and run. Both answer choice, score, noul, classify and route questions. winnow reads up to 64K tokens of state, against 8K tokens for standard-one. standard-one is the smaller model, at 8.0B parameters to 12B.
Which is more accurate, standard-one or winnow?
They report on different suites — standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2), winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, standard-one or winnow?
standard-one: Hosted, price not published, or free to self-host. winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, standard-one or winnow?
By their publishers’ figures, standard-one answers in about 25.8 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run standard-one or winnow locally?
Yes, both: systemone pull standard-thinking/standard-one and systemone pull eldanring/winnow download the weights.
