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.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
metask-jev
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
80.1%
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
62.8 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 metask-jev?
bespoke-nimble-9b is from Bespoke Labs and metask-jev from Metask Lab. bespoke-nimble-9b has open weights and a hosted API; metask-jev has open weights you can download and run. Both answer choice, noul, score, classify and route questions. bespoke-nimble-9b reads up to 8K tokens of state, against 4K tokens for metask-jev. metask-jev is the smaller model, at 4.5B parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or metask-jev?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or metask-jev?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or metask-jev?
By their publishers’ figures, metask-jev answers in about 62.8 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 metask-jev locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull metask-lab/metask-jev download the weights.
Evaluation suite
Bespoke held-out set (324 examples)
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
