Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
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
mira
rune
Fine-tuned from
jhu-clsp/mmbert-small
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
74.5%
—
Calibration error
0.025
—
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
—
Latest version
0.1.4
2026.09
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 mira and rune?
mira is from SAGEA and rune from Surogate (Invergent). mira 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.
Which is more accurate, mira or rune?
Only mira publishes an accuracy figure (74.5% on s1-decision-bench); rune does not, so there is no comparison to make without your own test.
Which is cheaper, mira or rune?
mira: 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 mira or rune locally?
Yes, both: systemone pull sagea/mira and systemone pull surogate/rune download the weights.