whatmodel.sh / decision / Bespoke-Nimble-9B (DecisionBench 594dfdcf)

Bespoke-Nimble-9B (DecisionBench 594dfdcf)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Bespoke-Nimble-9B (DecisionBench 594dfdcf) is an open-weights decision model from Bespoke Labs. Its published size is 9B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: bespokelabs/Bespoke-Nimble-9B, revision 594dfdcfb6f94e3d0c0db7535180d3c71689169a; decision-model; adapter nimble-hf; probability source native_candidate_logits_fp32_softmax. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

· Weights licence ↗ · Parameter count ↗

Published served parameter count; not a RAM or download-size measurement.

53.9±1.5#170 of 355 decision modelsfrom 32 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Bespoke-Nimble-9B (DecisionBench 594dfdcf), out of 357 with a score, then more from Bespoke Labs.

#modelscorewhereRAMreleased
170Solomon v1.1 Doccy Health54±1model files2026-09-21
171Sieve 4B Sthānika AI54±1model files2026-10-13
172Bespoke-Nimble-9B (DecisionBench 594dfdcf) Bespoke Labs54±2model files
173JevAny-Qwen-4B (pointer) (JevBench mini) SimpleJev54±2source code
174Standard One 3B SH (v4) Standard Thinking54±1model files
more from Bespoke Labs
15Bespoke Nimble v4 Max (27B) Bespoke Labs70±1model files2026-10
135Bespoke Nimble 9B v3 Bespoke Labs58±1local~21GB2026-10-06
186Bespoke-Nimble-9B (JevBench mini) Bespoke Labs53±2source code

see all decision models · find the ones that fit your machine

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #56 of 114 · 99% of its score · 32 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, JevK5 v0.3, Together Tev1 Qwen3.5-4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted58.0% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 39/56medium · avg 51%▇▇▇▇▇▇ 16%at its level
DecisionBench v1 · routing (all-request accuracy) submitted71.7% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 33/56medium · avg 64%▇▇▇▇ 11%sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted72.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 47/56medium · avg 58%▇▇▇▇ 8.9%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted45.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 39/56medium · avg 39%▇▇▇ 7.2%at its level
DecisionBench v1 · verification (all-request accuracy) submitted56.5% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 26/56medium · avg 56%▇▇ 5.1%blunt · at its level
Prevalence study · CLINC15096.2% ✎██·········█ beats 0/2very easy · avg 95%▇▇ 4.9%sharp · maxed out · small run
Prevalence study · TREC-687.2% ✎█··█·······█ beats 0/2easy · avg 84%▇▇ 4.6%sharp · small run
DecisionBench v1 · document record classification (all-request accuracy) submitted49.8% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 39/56medium · avg 46%▇▇ 4.1%at its level
24 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · triage (all-request accuracy) submitted79.0% ✎▁·▁·▂▃▄▃▃█▄▂ beats 28/56easy · avg 78%▇ 3.6%sharp
Prevalence study · FPB62.9% ✎█·········██ beats 0/2medium · avg 60%▇ 3.6%at its level · small run
DecisionBench v1 · completion assessment (all-request accuracy) submitted90.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 32/56very easy · avg 86%▇ 3.6%sharp
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted48.2% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 37/56medium · avg 45%▇ 3.4%at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted91.7% ✎▃▃▂·▁▁▁▁▁▃█▅ beats 26/56very easy · avg 86%▇ 3.1%sharp · noisy
Prevalence study · HWU6489.6% ✎█··········▄ beats 1/2very easy · avg 86%▇ 3.0%small run
Prevalence study · HateXplain47.0% ✎█·█········█ beats 1/2medium · avg 37%▇ 2.9%at its level · small run
DecisionBench v1 · content classification (all-request accuracy) submitted80.0% ✎▁····▁▁▁▁▁▁█ beats 47/56easy · avg 73%▇ 2.7%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted60.0% ✎▁······▂▃▅▇█ beats 42/56medium · avg 52%▇ 2.3%at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted22.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 25/56medium · avg 35%▇ 1.8%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted21.0% ✎▁▁·▁▁▁▃▁▃▁▁█ beats 27/56hard · avg 29%▇ 1.7%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted64.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 32/56medium · avg 62%▇ 1.5%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted29.3% ✎▂·▁▃▆█▅▃▃▂▁▁ beats 4/56medium · avg 52%▇ 1.0%at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted86.5% ✎█▁▂▁▁▁▁▁▂▅▁▁ beats 41/56easy · avg 74%▇ 0.6%noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted76.5% ✎█▄▃▁▁▃▂▂▁·▁▁ beats 45/56easy · avg 66%▇ 0.6%blunt · at its level
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted58.0% ✎▁▁▁▂▆▃▃█···▁ beats 32/56medium · avg 52%▇ 0.4%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted0.0% ✎▃·····▆█▂▂▄▇ beats 1/56easy · avg 77%▇ 0.3%noisy
DecisionBench v1 · document classification (all-request accuracy) submitted11.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 22/56hard · avg 21%▇ 0.3%blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted12.0% ✎▁·▁▃·▁▁█▂▃█▂ beats 2/56easy · avg 71%▇ 0.2%blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted0.0% ✎▃····▃▅▃▂▂·█ beats 1/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted0.0% ✎▃·····▁▇▆▁█▃ beats 1/56easy · avg 73%▇ 0.1%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted48.9% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 21/56easy · avg 66%▇ 0.1%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted49.1% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 18/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted0.0% ✎█▁···▁·▂▆▅▂▂ beats 10/56medium · avg 42%▇ 0.0%blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. This is the revision recorded by the benchmark. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/bespokelabs ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 80%, Typed Decision Models under P… 19%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified27CC0 1.0
Typed Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit Priors5CC-BY-4.0
prior · pull toward the middle
weighted average= 53.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json