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.
Uprelic's hosted decision API, run on GPUs in Paris. Answers noul, choice and score questions about text, JSON and up to 8 images, with a probability for every option and no generated text, on the same request shape as Jev. No weights; base model and size not disclosed.
Decides
choice, rank, route
choice, score, noul, classify, route
Architecture
modernjev
strom
Fine-tuned from
answerdotai/modernbert-base
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
73.4%
87.0%
Calibration error
—
0.033
Valid action rate
—
—
Median latency
—
136 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 strom?
modernjev-decide is from Maziyar Panahi and strom from Uprelic. modernjev-decide has open weights you can download and run; strom is only available as a hosted API. Both answer choice and route questions. Only modernjev-decide answers rank. Only strom answers score, noul and classify. strom reads up to 32K tokens of state, against 4K tokens for modernjev-decide. modernjev-decide is licensed apache-2.0; strom, proprietary.
Which is more accurate, modernjev-decide or strom?
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), strom 87.0% on JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, modernjev-decide or strom?
modernjev-decide: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run modernjev-decide or strom locally?
modernjev-decide yes — systemone pull maziyar-panahi/modernjev-decide downloads its weights. The other is only served as a hosted API.
Evaluation suite
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
