An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
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
choice, score, noul, classify, route
Architecture
open-jev
rune
Fine-tuned from
microsoft/deberta-v3-large
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
85.4%
—
Calibration error
0.022
—
Valid action rate
—
—
Median latency
28 ms
—
p95 latency
—
—
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 open-jev-deberta-v3-large and rune?
open-jev-deberta-v3-large is from Kotoba Labs and rune from Surogate (Invergent). open-jev-deberta-v3-large has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul and classify questions. Only rune answers route. rune reads up to 262K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 26B.
Which is more accurate, open-jev-deberta-v3-large or rune?
Only open-jev-deberta-v3-large publishes an accuracy figure (85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)); rune does not, so there is no comparison to make without your own test.
Which is cheaper, open-jev-deberta-v3-large or rune?
open-jev-deberta-v3-large: 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 open-jev-deberta-v3-large or rune locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull surogate/rune download the weights.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
