whatmodel.sh / decision / vLLM-SR Decision 2.0 Lux 9B

vLLM-SR Decision 2.0 Lux 9B

+ contribute

vLLM-SR Decision 2.0 Lux 9B is an open-weights decision model from vLLM Semantic Router. Its published size is 9.65B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine decision-2.0-lux-9b; reported model vLLM-SR Decision 2.0 Lux 9B. Type: full fine-tune; 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:lux, manifest 4148abeac890bfcf50bab4fdae636336468b21a9291f9a3f42ae526b17fd32a8, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (20349 MiB, rounded upward to 19.9 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.

53.7±1.1#174 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 Lux 9B, out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM
174	Standard One 3B SH (v4) Standard Thinking	54±1	model files
175	decider-4b v2.1 (JevBench mini) Mapika	54±2	source code
176	vLLM-SR Decision 2.0 Lux 9B vLLM Semantic Router	54±1	local	~20GB
177	JevAny-Gemma-4B (pointer) (JevBench mini) SimpleJev	54±2	source code
178	JPT-9B Qwen3.5-9B LoRA kirp	54±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▁▃▁▁▁▂▃▄▆██▆ #133 of 250 · 6.4% of its score · 6 tests

Beats Tern-35B-A3B, Cerno 4B v1.1, Trio-Spark DI (9B) here, though they rank higher overall. Trails Amber 0.4B, OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B 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	71.3% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 94/236	easy · avg 70%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	94.0% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 117/246	very easy · avg 92%	▇ 1.7%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	27.3% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 101/243	medium · avg 37%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	56.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 59/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	66.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 173/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.7% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #173 of 258 · 5.3% of its score · 7 tests

Beats Solar Decide, JevK5 9B v0.3.3 here, though they rank higher overall. Trails Mola-68M, Bosun v3.1 1.7B LoRA, Dinah-1 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	44.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 146/246	medium · avg 38%	▇ 1.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	44.6% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 81/246	medium · avg 47%	▇ 1.8%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	82.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 166/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	59.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 83/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	89.9% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 124/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	84.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 130/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	64.2% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #132 of 256 · 19% of its score · 9 tests

Beats Solar Decide, muria (Gemma 4 12B), Winnow-12B here, though they rank higher overall. 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: HellaSwag (accuracy) submitted	88.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 124/246	very easy · avg 85%	▇▇ 4.6%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	81.7% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 164/246	easy · avg 74%	▇▇ 4.5%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	64.6% ✎	▁▂▃▅▅█▂····▁ beats 127/246	medium · avg 60%	▇▇ 4.4%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	43.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 103/246	medium · avg 44%	▇ 1.9%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	11.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 65/246	hard · avg 22%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	76.1% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 128/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	44.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 58/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	64.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 75/246	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	82.7% ✎	▁···▁▁▁▁▃▆█▃ beats 85/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #157 of 247 · 7.7% of its score · 6 tests

Beats Jegue 0.1 (9B), Standard One 8B SH (v4), Sieve 4B here, though they rank higher overall. Trails Crivo-32M v2, Crivo-68M, Crivo-150M v2 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	65.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 129/246	medium · avg 61%	▇ 3.3%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 136/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	80.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 90/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	62.7% ✎	▁········▁▇█ beats 137/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	22.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 133/237	hard · avg 21%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	39.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 55/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #125 of 263 · 43% of its score · 19 tests

Beats Winnow-12B (DecisionBench b6ac22b0), Cerno 4B v1.1, CoCo-Decision-4B 2.4 here, though they rank higher overall. Trails PurpleMIST-Flash-1.0, JPT-9B Qwen3.5-9B LoRA 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	52.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 123/246	medium · avg 46%	▇▇▇ 8.5%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	75.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 123/246	easy · avg 70%	▇▇ 6.0%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	70.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 133/246	easy · avg 66%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	94.4% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 133/246	very easy · avg 90%	▇ 3.6%	sharp · maxed out
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	59.4% ✎	▁··▄█▆▆▆▅▅▃▁ beats 157/246	medium · avg 45%	▇ 2.8%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	87.5% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 177/246	easy · avg 78%	▇ 2.7%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	40.8% ✎	▂▆▅▅▆█▆▃▁··▁ beats 118/246	medium · avg 39%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 137/246	very easy · avg 96%	▇ 1.9%	sharp · maxed out · noisy

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	74.4% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 18/25	easy · avg 69%	▇ 1.8%	at its level
Ollaya · BoolQ	86.7% ✎	▁··▃▃▁▄▁▃█▇▄ beats 18/25	easy · avg 84%	▇ 1.4%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	32.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 181/246	hard · avg 22%	▇ 1.1%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	56.8% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 96/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	59.0% ✎	██▄▃▃▄▁▁···▁ beats 141/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	66.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 104/246	easy · avg 71%	▇ 0.8%	at its level
Ollaya · SQuAD 2 answerability	86.3% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 21/25	easy · avg 80%	▇ 0.7%	blunt
Ollaya · VitaminC verification	78.3% ✎	▁···▃·▄█▃··▁ beats 17/25	easy · avg 78%	▇ 0.7%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	12.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 86/246	hard · avg 16%	▇ 0.5%	blunt
Ollaya · MultiNLI	90.6% ✎	▂··▄██▂▆▆█▆▂ beats 20/25	very easy · avg 87%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	7.6% ✎	▃▁▂▃▆█▇▅▅▃▁▁ beats 3/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #59 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	70.7% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 19/22	medium · avg 64%	▇ 2.9%	at its level
Ollaya · PAWS paraphrase	80.8% ✎	▂▂▂▂·▃█▆·▂·▁ beats 12/25	easy · avg 81%	▇ 1.7%	typical
Ollaya · SummEval relevance	44.6% ✎	▁··▁▂▁▅··▃██ beats 13/25	medium · avg 41%	▇ 1.7%	at its level
Ollaya · Aegis 2 safety	86.8% ✎	▂·▁▁▂·▃▃▂█▃▃ beats 25/25	easy · avg 77%	▇ 1.4%	typical
Ollaya · MASSIVE German intent	83.4% ✎	▁····▁·▂▃▆█▃ beats 14/23	easy · avg 84%	▇ 1.4%	sharp
Ollaya · SummEval consistency	81.9% ✎	▁·▁▁··▁▁▁▁▄█ beats 16/25	easy · avg 75%	▇ 0.8%	sharp · noisy
Ollaya · MASSIVE English intent	84.3% ✎	▁·······▂▃█▃ beats 10/23	very easy · avg 86%	▇ 0.7%	noisy
Ollaya · HelpSteer 2 scoring	34.5% ✎	▁▁··▁·▁▃▇█▅▄ beats 8/23	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	70.0% ✎	▂▂▃·▂▅▅▆▃▅·█ beats 2/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 6.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	46.8500 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 129/247	avg 41.206 points	▇▇ 4.3%	blunt
Decision Index 0.4.1: private new domains (equated points)	44.6600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 142/247	avg 38.861 points	▇ 2.4%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 19.9 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run decision2:lux --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 16%

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	▇▇▇▇▇ 16%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 53.7

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.7%	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]	64.2%	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