All models

COMPARE

2 models, side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertymapika/deciderbespoke-labs/bespoke-nimble-9b
SummaryThe most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.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.
Decideschoice, score, noul, classify, routechoice, noul, score, classify, route
Architecturedecidernimble
Fine-tuned fromqwen/qwen3.5-2b-baseqwen/qwen3.5-9b
Licenseapache-2.0apache-2.0
AvailabilityOpen weightsOpen weights + hosted API
Hosted by—Bespoke Labs
Input price——
Decision accuracy80.2%90.1%
Calibration error0.0380.054
Valid action rate——
Median latency3.2 ms106 ms
p95 latency——
Evaluation suiteDecider 67-task regression setBespoke held-out set (324 examples)
Latest version2026.092026.09
Variants—SHA256SUMS
Size of latest version3.5 GB184.3 MB
Files410
Downloads00
Stars00
Tagssystem-one, qwen, rl, calibrated, 2bsystem-one, qwen, lora, curated-data, 9b
UpdatedSep 25, 2026Sep 25, 2026