A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
rune
Fine-tuned from
qwen/qwen3.5-2b-base
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
75.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
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 decider and rune?
decider is from Mapika and rune from Surogate (Invergent). decider has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. rune reads up to 262K tokens of state, against 32K tokens for decider. decider is the smaller model, at 1.9B parameters to 26B.
Which is more accurate, decider or rune?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); rune does not, so there is no comparison to make without your own test.
Which is cheaper, decider or rune?
decider: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run decider or rune locally?
Yes, both: systemone pull mapika/decider and systemone pull surogate/rune download the weights.
