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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
state-decider
Fine-tuned from
qwen/qwen3.5-9b
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Bespoke Labs
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
90.1%
76.8%
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
—
p95 latency
—
—
Evaluation suite
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 state-decider-1?
bespoke-nimble-9b is from Bespoke Labs and state-decider-1 from meraGPT. bespoke-nimble-9b has open weights and a hosted API; state-decider-1 is only available as a hosted API. Both answer choice, noul, score, classify and route questions. bespoke-nimble-9b reads up to 8K tokens of state, against 4K tokens for state-decider-1. bespoke-nimble-9b is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, bespoke-nimble-9b or state-decider-1?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or state-decider-1?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or state-decider-1 locally?
bespoke-nimble-9b yes — systemone pull bespoke-labs/bespoke-nimble-9b downloads its weights. The other is only served as a hosted API.
Bespoke held-out set (324 examples)
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
