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.
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, route
choice, score, noul, classify, route
Architecture
standard-one
state-decider
Fine-tuned from
mistralai/ministral-3-8b-instruct-2512-bf16
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Standard Thinking
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
71.1%
76.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
25.8 ms
—
p95 latency
41.9 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 standard-one and state-decider-1?
standard-one is from Standard Thinking and state-decider-1 from meraGPT. standard-one has open weights and a hosted API; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. standard-one reads up to 8K tokens of state, against 4K tokens for state-decider-1. standard-one is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, standard-one or state-decider-1?
They report on different suites — standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2), 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, standard-one or state-decider-1?
standard-one: Hosted, price not published, or free to self-host. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run standard-one or state-decider-1 locally?
standard-one yes — systemone pull standard-thinking/standard-one downloads its weights. The other is only served as a hosted API.
