whatmodel.sh / decision / vLLM-SR d3-turbo v1.1 (27B)

vLLM-SR d3-turbo v1.1 (27B)

+ contribute

vLLM-SR d3-turbo v1.1 (27B) is an open-weights decision model from vLLM Semantic Router. Its published size is 26.09B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine vllm-sr-d3-turbo-v11; reported model vLLM-SR d3-turbo v1.1 (27B). Type: full fine-tune; technique: autoregressive. Comparison entry; no current run command, 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.

Model information sources

· Weights licence ↗ · Parameter count ↗

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

71.9±1.4#9 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of vLLM-SR d3-turbo v1.1 (27B), out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM	released
7	StartLux-Decision v1.1 27B StartLux	73±1	model files
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
10	Perplexity Decider v1.1 (27B) Perplexity	72±1	api price unknown		2026-10-05
11	WeMM-JEV-27B Rover00	71±1	model files
	more from vLLM Semantic Router
25	vLLM-SR d3 (27B) vLLM Semantic Router	69±1	model files
97	vLLM-SR Decision 2.0 Vega 27B vLLM Semantic Router	61±1	model files
103	vLLM-SR d3-flash (9B) vLLM Semantic Router	61±1	local	~18GB

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #34 of 250 · 4.3% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni 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	85.4% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 175/236	easy · avg 70%	▇ 1.2%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	68.8% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 217/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	89.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 216/246	easy · avg 72%	▇ 0.7%	noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	100.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 231/243	medium · avg 37%	▇ 0.7%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.7% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 213/246	very easy · avg 92%	▇ 0.6%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.5% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #16 of 258 · 7.1% of its score · 7 tests

Beats Fastino GLiDE 1.2, KnowLine 31B Gen1, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails StartLux-Decision v1.1 4B, VisionJEV 1.0.0 (27B), OneShot 27B 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	48.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 202/246	medium · avg 38%	▇ 3.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	61.8% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 230/246	medium · avg 47%	▇ 2.6%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	88.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 227/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	96.2% ✎	█▅▅▄▃▂▁▃▁▁·▁ beats 234/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	93.8% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 233/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	96.9% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 232/238	easy · avg 83%	▇ 0.2%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	16.1% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #2 of 256 · 18% of its score · 9 tests

Beats Jeffan-31b-1710, Sieve 31B v3, Fastino GLiDE 1.2 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	80.2% ✎	▁▂▃▅▅█▃····▁ beats 238/246	medium · avg 60%	▇▇ 4.6%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	86.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 235/246	easy · avg 74%	▇▇ 4.3%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	65.0% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 205/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	98.2% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 240/246	very easy · avg 85%	▇ 1.9%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	64.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 242/246	hard · avg 22%	▇ 1.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	80.4% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 226/246	medium · avg 62%	▇ 0.9%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	85.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 235/246	easy · avg 71%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	82.3% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 203/246	easy · avg 66%	▇ 0.6%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	95.3% ✎	▁···▁▁▁▁▃▆█▃ beats 236/246	easy · avg 84%	▇ 0.4%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #53 of 247 · 9.0% of its score · 6 tests

Trails Kas 4B, baselabs joey-1 (2B), Clef-flash 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	83.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 237/246	medium · avg 61%	▇ 3.4%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	66.9% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 224/246	medium · avg 60%	▇ 2.2%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	70.9% ✎	▁········▁▇█ beats 244/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	73.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 197/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 191/246	easy · avg 83%	▇ 0.6%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	61.6% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 215/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #15 of 263 · 35% of its score · 14 tests

Beats StartLux-Decision v1.1 27B here, though they rank higher overall. Trails d1 (hosted), Jev 1.13, Matilda Decision v1 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	73.0% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 227/246	medium · avg 46%	▇▇▇▇ 9.4%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	89.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 232/246	easy · avg 66%	▇▇ 4.7%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	88.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 225/246	easy · avg 70%	▇▇ 4.4%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	59.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 243/246	medium · avg 39%	▇▇ 4.0%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	84.5% ✎	▁··▄█▆▆▆▅▅▃▁ beats 231/246	medium · avg 45%	▇ 3.0%	sharp
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	43.8% ✎	▁▁▁▁▁▁▁▂▅█▃▁ beats 234/246	hard · avg 22%	▇ 2.2%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	95.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 237/246	easy · avg 78%	▇ 2.1%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	70.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 219/246	medium · avg 60%	▇ 1.3%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.0% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 194/246	very easy · avg 90%	▇ 1.1%	sharp · maxed out
Decision Index 0.4.1: ChessBench (accuracy) submitted	24.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 213/246	hard · avg 16%	▇ 1.0%	blunt
Decision Index 0.4.1: CRUXEval (accuracy) submitted	86.0% ✎	██▄▃▃▄▁▁···▁ beats 217/246	medium · avg 58%	▇ 1.0%	noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	92.8% ✎	▁███▆▅▃▃▃▁▁▁ beats 230/246	easy · avg 71%	▇ 0.8%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 237/246	very easy · avg 96%	▇ 0.4%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	16.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 220/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #16 of 79 · 15% of its score · 12 tests

Beats StartLux-Decision v1.1 27B here, though they rank higher overall. Trails Clef-flash, Mercury Decide (free endpoint), Clef here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	85.0600 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 53/61	avg 63.423 points	▇ 1.9%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	44.0500 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 50/61	avg 22.797 points	▇ 1.8%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	84.7500 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 48/61	avg 66.987 points	▇ 1.6%	blunt
Decision Index Vision 0.4: private same skills (points)	68.0800 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 54/61	avg 48.067 points	▇ 1.6%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	50.8700 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 50/61	avg 28.443 points	▇ 1.4%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	72.2500 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 50/61	avg 53.651 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	80.9500 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 55/61	avg 62.137 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	96.7200 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 46/61	avg 83.859 points	▇ 1.0%	blunt

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	39.0000 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 57/61	avg 19.676 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	73.5800 points ✎	▁···▁▂▂▂█▄▂▃ beats 56/61	avg 44.994 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	82.3500 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 61/61	avg 67.662 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	92.1900 points ✎	▁··▁▁▁▁▁▂▄█▁ beats 39/61	avg 85.184 points	▇ 0.5%	blunt

other tests2 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)	63.9800 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 234/247	avg 41.206 points	▇▇▇ 6.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	72.3100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 220/247	avg 38.861 points	▇ 3.7%	blunt

$ where to run it

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. 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/vllm-sr ↗

$ how the score was worked out · Decision Index 0.4.1 84%, Decision Index Vision 0.4 15%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 84%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇▇▇ 15%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 71.9

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.5%	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]	16.1%	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