A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
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.
Decides
choice, rank, route
choice, score, noul, classify
Architecture
modernjev
open-jev
Fine-tuned from
answerdotai/modernbert-base
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.4%
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 modernjev-decide and open-jev-deberta-v3-large?
modernjev-decide is from Maziyar Panahi and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice questions. Only modernjev-decide answers rank and route. Only open-jev-deberta-v3-large answers score, noul and classify. modernjev-decide reads up to 4K tokens of state, against 512 tokens for open-jev-deberta-v3-large. modernjev-decide is the smaller model, at 150M parameters to 434M.
Which is more accurate, modernjev-decide or open-jev-deberta-v3-large?
They report on different suites — modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split), open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, modernjev-decide or open-jev-deberta-v3-large?
modernjev-decide: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run modernjev-decide or open-jev-deberta-v3-large locally?
Yes, both: systemone pull maziyar-panahi/modernjev-decide and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
—
Evaluation suite
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
