whatmodel.sh / decision / Bespoke Nimble 9B v3

Bespoke Nimble 9B v3

+ contribute

Bespoke Nimble 9B v3 is an open-weights decision model from Bespoke Labs, released 6 October 2026. Its published size is 9.65B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine nimble-v3; reported model Bespoke Nimble 9B v3. Type: LoRA; technique: autoregressive. No API price or speed inferred from the benchmark. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run. Reviewed Ollaya local route added 2026-10-31: nimble:9b-v3, manifest 01cb73cdc839e8eb25a6209976a2cd1e83048b6b893c809d7144e71b34ff2b31, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (21188 MiB, rounded upward to 20.7 GiB) on RTX 5090 during the short five-question triage workload, not download size or a maximum-context guarantee. Runtime installation is required; no fresh execution performed here. Historical benchmark adapter and input protocol still vary by result.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

57.6±1.2#133 of 355 decision modelsfrom 58 benchmark results across 3 sources

$ how it compares

The decision models ranked either side of Bespoke Nimble 9B v3, out of 357 with a score, then more from Bespoke Labs.

#	model	score	where	RAM	released
133	Nace.AI Drex v1.5 Nace.AI	58±1	model files
134	Clef-flash Cloudflare	58±1	api $0.038/M input tokens +local	~25GB	2026-10
135	Bespoke Nimble 9B v3 Bespoke Labs	58±1	local	~21GB	2026-10-06
136	simplejev-qwen3.6-35b-a3b (DecisionBench 995ad96e) featherless-ai	58±2	model files
137	Sieve 9B v2 Sthānika AI	57±1	model files		2026-10-13
	more from Bespoke Labs
15	Bespoke Nimble v4 Max (27B) Bespoke Labs	70±1	model files		2026-10
172	Bespoke-Nimble-9B (DecisionBench 594dfdcf) Bespoke Labs	54±2	model files
186	Bespoke-Nimble-9B (JevBench mini) Bespoke Labs	53±2	source code

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #45 of 250 · 5.8% of its score · 6 tests

Beats Fastino GLiDE 1.2, vLLM-SR d3-ultra (Decision 3.0, 27B), AutoTrust-JEV-27B v1.1 here, though they rank higher overall. Trails baselabs joey-1 (2B), Solomon v1.1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: API-Bank (accuracy) submitted	79.1% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 115/236	easy · avg 70%	▇ 1.8%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 202/246	very easy · avg 92%	▇ 1.3%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	98.9% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 224/243	medium · avg 37%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	86.8% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 189/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	68.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 213/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	76.5% ✎	no other model yet		—	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

retrieval & classification▁▁▁·▁▁▁▁▃▃█▅ #63 of 258 · 5.5% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, oenogarum (Gemma 4 31B), Aleria Judge 1.1.1 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	38.8% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 92/246	medium · avg 38%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	58.3% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 192/246	medium · avg 47%	▇ 1.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	84.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 181/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	53.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 66/245	easy · avg 70%	▇ 0.4%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	88.3% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 104/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	83.7% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 125/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	71.8% ✎	no other model yet		—	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

language understanding▂▂▂▃▂▅▆▃█▆▄▃ #129 of 256 · 18% of its score · 9 tests

Trails vLLM-SR d3-nano (2B), JevK5 v0.3, Decider 4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	70.3% ✎	▁▂▃▅▅█▂····▁ beats 161/246	medium · avg 60%	▇▇ 4.4%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	82.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 181/246	easy · avg 74%	▇▇ 4.4%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	88.8% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 125/246	very easy · avg 85%	▇▇ 3.8%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	53.5% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 148/246	medium · avg 44%	▇ 2.0%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	39.0% ✎	▁··▂▃▃▅▇█▇▃▃ beats 196/246	hard · avg 22%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	74.1% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 105/246	easy · avg 71%	▇ 0.9%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	73.1% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 156/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	76.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 138/246	easy · avg 66%	▇ 0.6%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	90.4% ✎	▁···▁▁▁▁▃▆█▃ beats 151/246	easy · avg 84%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #102 of 247 · 7.8% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B), decisio 0.6.0 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B), Crivo-400M, Amber 0.4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	61.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 112/246	medium · avg 61%	▇ 3.3%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 138/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	64.0% ✎	▁········▁▇█ beats 162/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	90.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 146/246	easy · avg 83%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: POP909-CL (accuracy) submitted	74.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 199/237	hard · avg 21%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	36.2% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 22/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #107 of 263 · 41% of its score · 19 tests

Beats Senova-4B v2, OneJev1.6-4B, Seb-9B v2 here, though they rank higher overall. Trails Decider 35B-A3B, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), Solar Decide here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	60.1% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 158/246	medium · avg 46%	▇▇▇▇ 8.8%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	79.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 147/246	easy · avg 70%	▇▇ 5.5%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	84.5% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 213/246	easy · avg 66%	▇▇ 5.1%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	59.0% ✎	▁··▄█▆▆▆▅▅▃▁ beats 156/246	medium · avg 45%	▇ 2.9%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	46.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 164/246	medium · avg 39%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	95.6% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 152/246	very easy · avg 90%	▇ 2.7%	sharp · maxed out
Decision Index 0.4.1: WinoGrande (accuracy) submitted	86.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 171/246	easy · avg 78%	▇ 2.5%	typical
Ollaya · PubMedQA	74.8% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 19/25	easy · avg 69%	▇ 1.8%	typical

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · BoolQ	86.0% ✎	▁··▃▃▁▄▁▃█▇▄ beats 16/25	easy · avg 84%	▇ 1.3%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 142/246	very easy · avg 96%	▇ 1.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	25.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 109/246	hard · avg 22%	▇ 1.3%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	58.8% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 121/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	64.7% ✎	██▄▃▃▄▁▁···▁ beats 153/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	75.0% ✎	▁███▆▅▃▃▁▁▁▁ beats 156/246	easy · avg 71%	▇ 0.8%	typical
Ollaya · SQuAD 2 answerability	81.3% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 17/25	easy · avg 80%	▇ 0.7%	blunt
Ollaya · VitaminC verification	79.5% ✎	▁···▃·▄█▃··▁ beats 20/25	easy · avg 78%	▇ 0.7%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	14.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 110/246	hard · avg 16%	▇ 0.6%	blunt
Ollaya · MultiNLI	89.0% ✎	▂··▄██▂▆▆█▆▂ beats 17/25	very easy · avg 87%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 84/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #67 of 114 · 11% of its score · 9 tests

Beats Clef-omni here, though they rank higher overall. Trails InternLM Intern-Decision Qwen3.5-4B, StartLux-Decision v1.1 0.8B, Kev 4B r10 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	64.8% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 12/22	medium · avg 64%	▇ 2.9%	at its level
Ollaya · SummEval relevance	37.5% ✎	▁··▁▂▁▅··▃██ beats 10/25	medium · avg 41%	▇ 1.8%	at its level
Ollaya · PAWS paraphrase	81.6% ✎	▂▂▂▂·▃█▆·▂·▁ beats 14/25	easy · avg 81%	▇ 1.6%	typical
Ollaya · Aegis 2 safety	74.0% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 11/25	easy · avg 77%	▇ 1.4%	typical
Ollaya · MASSIVE German intent	84.0% ✎	▁····▁·▂▃▆█▃ beats 15/23	easy · avg 84%	▇ 1.2%	sharp
Ollaya · SummEval consistency	76.4% ✎	▁·▁▁··▁▁▁▁▄█ beats 9/25	easy · avg 75%	▇ 0.7%	sharp · noisy
Ollaya · HelpSteer 2 scoring	41.0% ✎	▁▁··▁·▁▃▇█▅▄ beats 18/23	medium · avg 38%	▇ 0.7%	blunt · at its level
Ollaya · MASSIVE English intent	86.3% ✎	▁·······▂▃█▃ beats 16/23	very easy · avg 86%	▇ 0.6%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Civil Comments	89.0% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 15/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests4 not in a task · 10% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	51.8900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 155/247	avg 41.206 points	▇▇ 4.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	49.8200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 158/247	avg 38.861 points	▇ 2.5%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	56.5401 points ✎	▃···▃·▃▃█▅▅█ beats 6/13	avg 32.166 points	▇ 2.0%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	77.0457 points ✎	▂······▃▆▂██ beats 1/13	avg 70.133 points	▇ 0.6%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 20.7 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run nimble:9b-v3 --preset triage "The customer requests a refund."

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A matching Ollaya runtime manifest and published short-workload GPU memory measurement were reviewed separately; see local variants and identity_note. The command was not executed in this review. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/bespokelabs ↗

$ how the score was worked out · Decision Index 0.4.1 81%, Ollaya · original runs 16%, Benchmark Heaven (own decisio… 3%

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

source	results	share of the score	licence
Decision Index 0.4.1 · submitted; independent execution unverified	42	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%	CC BY 4.0
Ollaya · original runs	14	▇▇▇▇▇ 16%	Apache-2.0
Benchmark Heaven (own decision evaluations)	2	▇ 3%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 57.6

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	76.5%	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json
Decision Index 0.4.1	Decision Index 0.4.1: SGD/SGD-X (macro-F1) [correct]	71.8%	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-11-03 02:37 UTC · sources and licences · json