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.
A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, score, noul, classify
choice, score, noul, rank, extract
Architecture
open-jev
solvi
Fine-tuned from
microsoft/deberta-v3-large
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.4%
59.4%
Calibration error
0.022
0.210
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 solvi?
open-jev-deberta-v3-large is from Kotoba Labs and solvi from solvi. Both have open weights you can download and run. Both answer choice, score and noul questions. Only open-jev-deberta-v3-large answers classify. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 434M.
Which is more accurate, open-jev-deberta-v3-large or solvi?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or solvi?
open-jev-deberta-v3-large: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run open-jev-deberta-v3-large or solvi locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
