whatmodel.sh / decision / vLLM-SR Decision 2.0 Nox 4B

vLLM-SR Decision 2.0 Nox 4B

+ contribute

vLLM-SR Decision 2.0 Nox 4B is an open-weights decision model from vLLM Semantic Router. Its published size is 4.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine decision-2.0-nox-4b; reported model vLLM-SR Decision 2.0 Nox 4B. Type: LoRA + head; 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: decision2:nox, manifest d81d2a4fe5cad9b1e0e6a8c44d9108732a129328a9e595c935c4b6083b5e9133, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (12387 MiB, rounded upward to 12.1 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

· Weights licence ↗ · Parameter count ↗

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

50.6±1.1#198 of 355 decision modelsfrom 56 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of vLLM-SR Decision 2.0 Nox 4B, out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM
198	LiquidAI d1-3B Liquid AI	51±1	model files
199	djev-spark (DecisionBench 1444f3e9) mmastrac	51±2	source code
200	vLLM-SR Decision 2.0 Nox 4B vLLM Semantic Router	51±1	local	~12GB
201	Decider 4B Mapika	51±1	local	~11GB
202	Together Tev1 Qwen3.5-4B Together	51±1	model files
	more from vLLM Semantic Router
8	vLLM-SR d3-ultra (Decision 3.0, 27B) vLLM Semantic Router	72±1	model files
9	vLLM-SR d3-turbo v1.1 (27B) vLLM Semantic Router	72±1	model files
25	vLLM-SR d3 (27B) vLLM Semantic Router	69±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #170 of 250 · 6.7% of its score · 6 tests

Beats LiquidAI d1-3B here, though they rank higher overall. Trails JevK5 Lite, Gevva E2B, 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: BFCL (case exact accuracy) submitted	90.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 77/246	very easy · avg 92%	▇ 2.1%	sharp · maxed out · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	77.6% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 108/236	easy · avg 70%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	61.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 71/246	easy · avg 72%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	18.2% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 84/243	medium · avg 37%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.6% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 149/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	77.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #168 of 258 · 5.1% of its score · 7 tests

Beats Solar Decide, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), JevK5 9B v0.3.3 here, though they rank higher overall. Trails Bosun v3.1 1.7B LoRA, Dinah-1, DecisionTune 1.0 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	43.2% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 130/246	medium · avg 38%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	46.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 87/246	medium · avg 47%	▇ 1.7%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	80.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 146/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	55.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 73/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	87.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 100/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	78.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 79/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	61.5% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #164 of 256 · 20% of its score · 9 tests

Beats PurpleMIST-Flash-1.0, Hopper 12B (trained), Jev-Omni here, though they rank higher overall. Trails DecisionTune 1.0, Decider 2B, vLLM-SR d3-lite (0.8B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: HellaSwag (accuracy) submitted	81.4% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 90/246	very easy · avg 85%	▇▇ 5.3%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	79.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 150/246	easy · avg 74%	▇▇ 4.5%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	59.8% ✎	▁▂▃▅▅█▂····▁ beats 104/246	medium · avg 60%	▇▇ 4.3%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	39.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 89/246	medium · avg 44%	▇ 1.7%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	75.1% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 119/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	52.2% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 83/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	8.7% ✎	▁··▂▃▃▅▇█▇▃▃ beats 45/246	hard · avg 22%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	68.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 91/246	easy · avg 66%	▇ 0.7%	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	88.9% ✎	▁···▁▁▁▁▃▆█▃ beats 135/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #173 of 247 · 7.4% of its score · 6 tests

Trails Crivo-17M, Crivo-32M v2, Crivo-68M 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	59.3% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 98/246	medium · avg 61%	▇ 3.2%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 110/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	73.4% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 72/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	58.5% ✎	▁········▁▇█ beats 85/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	8.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 96/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	42.5% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 101/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #155 of 263 · 43% of its score · 19 tests

Beats StartLux-Decision v1.1 2B, Solomon v1.1, Standard One 3B SH (v4) here, though they rank higher overall. Trails Ryotide Qwen v0.3.1 (decision readout), Interfaze lev Qwen3.5-4B LoRA, razorback16 diffgemma (decision readout) 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	50.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 113/246	medium · avg 46%	▇▇▇ 7.9%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	71.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 100/246	easy · avg 70%	▇▇ 6.1%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	66.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 110/246	easy · avg 66%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	92.1% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 107/246	very easy · avg 90%	▇▇ 4.3%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	83.0% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 139/246	easy · avg 78%	▇ 2.7%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	58.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 154/246	medium · avg 45%	▇ 2.7%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 129/246	very easy · avg 96%	▇ 2.4%	sharp · maxed out · noisy
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	32.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 73/246	medium · avg 39%	▇ 2.3%	blunt · at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	72.4% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 16/25	easy · avg 69%	▇ 1.8%	at its level
Ollaya · BoolQ	83.3% ✎	▁··▃▃▁▄▁▃█▇▄ beats 10/25	easy · avg 84%	▇ 1.4%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	56.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 93/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	28.9% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 132/246	hard · avg 22%	▇ 1.0%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	53.3% ✎	██▄▃▃▄▁▁···▁ beats 123/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	66.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 105/246	easy · avg 71%	▇ 0.8%	at its level
Ollaya · SQuAD 2 answerability	75.3% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 10/25	easy · avg 80%	▇ 0.7%	blunt
Ollaya · VitaminC verification	76.3% ✎	▁···▃·▄█▃··▁ beats 11/25	easy · avg 78%	▇ 0.7%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	10.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 70/246	hard · avg 16%	▇ 0.5%	blunt
Ollaya · MultiNLI	89.6% ✎	▂··▄██▂▆▆█▆▂ beats 18/25	very easy · avg 87%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	9.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 17/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #57 of 114 · 11% of its score · 9 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.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	68.0% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 16/22	medium · avg 64%	▇ 2.9%	at its level
Ollaya · PAWS paraphrase	76.4% ✎	▂▂▂▂·▃█▆·▂·▁ beats 8/25	easy · avg 81%	▇ 1.7%	typical
Ollaya · SummEval relevance	47.1% ✎	▁··▁▂▁▅··▃██ beats 16/25	medium · avg 41%	▇ 1.6%	at its level
Ollaya · MASSIVE German intent	85.7% ✎	▁····▁·▂▃▆█▃ beats 17/23	easy · avg 84%	▇ 1.5%	sharp
Ollaya · Aegis 2 safety	84.0% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 23/25	easy · avg 77%	▇ 1.5%	typical
Ollaya · SummEval consistency	78.5% ✎	▁·▁▁··▁▁▁▁▄█ beats 11/25	easy · avg 75%	▇ 0.9%	sharp · noisy
Ollaya · MASSIVE English intent	86.0% ✎	▁·······▂▃█▃ beats 15/23	very easy · avg 86%	▇ 0.8%	noisy
Ollaya · HelpSteer 2 scoring	37.8% ✎	▁▁··▁·▁▃▇█▅▄ beats 12/23	medium · avg 38%	▇ 0.6%	blunt · at its level

1 more test

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Civil Comments	77.7% ✎	▂▂▂·▃▅▅▆▃▅·█ beats 3/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 6.3% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	43.1700 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 116/247	avg 41.206 points	▇▇ 4.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	37.1200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 112/247	avg 38.861 points	▇ 2.2%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 12.1 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run decision2:nox --preset triage "The customer requests a refund."

Download model files ↗
Published model files verified. 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/vllm-sr ↗

$ how the score was worked out · Decision Index 0.4.1 83%, Ollaya · original runs 17%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%	CC BY 4.0
Ollaya · original runs	14	▇▇▇▇▇ 17%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 50.6

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	77.8%	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]	61.5%	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