An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.
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, noul, score, classify, route
choice, score, noul, classify
Architecture
nimble
open-jev
Fine-tuned from
qwen/qwen3.5-9b
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
85.4%
Calibration error
0.054
0.022
Valid action rate
—
—
Median latency
106 ms
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 bespoke-nimble-9b and open-jev-deberta-v3-large?
bespoke-nimble-9b is from Bespoke Labs and open-jev-deberta-v3-large from Kotoba Labs. bespoke-nimble-9b has open weights and a hosted API; open-jev-deberta-v3-large has open weights you can download and run. Both answer choice, noul, score and classify questions. Only bespoke-nimble-9b answers route. bespoke-nimble-9b reads up to 8K 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 9.0B.
Which is more accurate, bespoke-nimble-9b or open-jev-deberta-v3-large?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), 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, bespoke-nimble-9b or open-jev-deberta-v3-large?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or open-jev-deberta-v3-large?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and bespoke-nimble-9b in about 106 ms — measured on different hardware, so treat it as a rough guide.
Can I run bespoke-nimble-9b or open-jev-deberta-v3-large locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
Bespoke held-out set (324 examples)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
