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 Situated World Model for fast judgment in agent loops.
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 trio-spark-v1?
standard-one is from Standard Thinking and trio-spark-v1 from MachineFi. standard-one has open weights and a hosted API; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only standard-one answers score and noul. standard-one reads up to 8K tokens of state, against 1K tokens for trio-spark-v1. standard-one is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, standard-one or trio-spark-v1?
Only standard-one publishes an accuracy figure (71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, standard-one or trio-spark-v1?
standard-one: Hosted, price not published, or free to self-host. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run standard-one or trio-spark-v1 locally?
standard-one yes — systemone pull standard-thinking/standard-one downloads its weights. The other is only served as a hosted API.
