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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
rune
xor
Fine-tuned from
google/gemma-4-26b-a4b-it
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Invergent
—
Input price
—
—
Decision accuracy
—
90.0%
Calibration error
—
0.073
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
162 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 rune and xor?
rune is from Surogate (Invergent) and xor from Juspay. rune has open weights and a hosted API; xor has open weights you can download and run. Both answer choice, score, noul, classify and route questions. rune is the smaller model, at 26B parameters to 35B.
Which is more accurate, rune or xor?
Only xor publishes an accuracy figure (90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2); rune does not, so there is no comparison to make without your own test.
Which is cheaper, rune or xor?
rune: Hosted, price not published, or free to self-host. xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run rune or xor locally?
Yes, both: systemone pull surogate/rune and systemone pull juspay/xor download the weights.
JevBench public set (231 items), maker's self-run of Xor 1.2
