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

vLLM-SR d3 (27B)

+ contribute

vLLM-SR d3 (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-v310; reported model vLLM-SR d3 (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.

68.7±1.4#25 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

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

#	model	score	where	released
23	OneJev1.6-27B OmniJev	69±2	model files	2026-10-17
24	baselabs elephant-1 (9B) baselabs	69±1	model files	2026-10-21
25	vLLM-SR d3 (27B) vLLM Semantic Router	69±1	model files
26	Amos 1 Large (27B) mukaddamzaid	69±1	model files	2026-09-30
27	AJev lm6q (Gemma 4 31B) andyzhang232	69±2	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
97	vLLM-SR Decision 2.0 Vega 27B vLLM Semantic Router	61±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #50 of 250 · 4.7% of its score · 6 tests

Beats 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, Bespoke Nimble 9B v3 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	86.4% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 201/236	easy · avg 70%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	69.1% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 221/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	80.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 195/243	medium · avg 37%	▇ 0.8%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	86.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 181/246	easy · avg 72%	▇ 0.8%	noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 197/246	very easy · avg 92%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #45 of 258 · 6.9% of its score · 7 tests

Beats H2O Lightning 31B v1.1, AutoTrust-JEV-27B v1.1, MISA AI 2.0 Decision Plus · oak 1.1 (31B) 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	49.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 221/246	medium · avg 38%	▇ 2.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	59.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 205/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	83.5% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 174/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	73.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 145/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	92.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 214/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	96.9% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 233/238	easy · avg 83%	▇ 0.2%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	57.3% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #6 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	76.0% ✎	▁▂▃▅▅█▂····▁ beats 204/246	medium · avg 60%	▇▇ 4.7%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	86.0% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 222/246	easy · avg 74%	▇▇ 4.4%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	66.8% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 214/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	98.2% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 243/246	very easy · avg 85%	▇ 2.2%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	30.0% ✎	▁··▂▃▃▅▇█▇▃▃ beats 166/246	hard · avg 22%	▇ 1.7%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	74.8% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 168/246	medium · avg 62%	▇ 0.9%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	78.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 149/246	easy · avg 71%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	82.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 201/246	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	95.7% ✎	▁···▁▁▁▁▃▆█▃ beats 240/246	easy · avg 84%	▇ 0.4%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #39 of 247 · 9.0% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), Nace.AI Drex Max v1 (27B) here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Xor 1.2 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	82.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 230/246	medium · avg 61%	▇ 3.4%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	63.7% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 187/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.6% ✎	▁········▁▇█ beats 193/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	62.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 183/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 207/246	easy · avg 83%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	41.6% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 90/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #17 of 263 · 36% of its score · 14 tests

Beats StartLux-Decision v1.1 27B, KnowLine 35B-A3B Gen1.5, Nace.AI Drex Max v1 (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 230/246	medium · avg 46%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	85.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 218/246	easy · avg 66%	▇▇ 4.9%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	88.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 233/246	easy · avg 70%	▇▇ 4.8%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	56.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 240/246	medium · avg 39%	▇ 3.7%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	85.2% ✎	▁··▄█▆▆▆▅▅▃▁ beats 233/246	medium · avg 45%	▇ 3.2%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	95.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 240/246	easy · avg 78%	▇ 2.3%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	38.4% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 218/246	hard · avg 22%	▇ 2.0%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.4% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 223/246	very easy · avg 90%	▇ 1.3%	sharp · maxed out

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	69.3% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 211/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	88.1% ✎	██▄▃▃▄▁▁···▁ beats 233/246	medium · avg 58%	▇ 1.0%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	17.6% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 144/246	hard · avg 16%	▇ 0.9%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	81.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 185/246	easy · avg 71%	▇ 0.9%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 240/246	very easy · avg 96%	▇ 0.5%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	14.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 173/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #24 of 79 · 14% of its score · 12 tests

Trails Clef-flash, Perplexity Decider Flash v1.2 (4B), Mercury Decide (free endpoint) 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	83.2800 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 44/61	avg 63.423 points	▇ 1.8%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	46.3700 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 57/61	avg 22.797 points	▇ 1.7%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	85.7500 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 54/61	avg 66.987 points	▇ 1.5%	blunt
Decision Index Vision 0.4: private same skills (points)	68.4500 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 56/61	avg 48.067 points	▇ 1.5%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	44.6000 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 47/61	avg 28.443 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	73.9200 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 56/61	avg 53.651 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	79.4500 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 49/61	avg 62.137 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	97.8100 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 55/61	avg 83.859 points	▇ 0.9%	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	33.4000 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 46/61	avg 19.676 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	60.2100 points ✎	▁···▁▂▂▂█▄▂▃ beats 46/61	avg 44.994 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	76.3600 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 42/61	avg 67.662 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	92.5900 points ✎	▁··▁▁▁▁▁▂▄█▁ beats 49/61	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)	62.5000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 228/247	avg 41.206 points	▇▇ 6.2%	blunt
Decision Index 0.4.1: private new domains (equated points)	74.1100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 233/247	avg 38.861 points	▇ 3.4%	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 85%, Decision Index Vision 0.4 14%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇▇ 14%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 68.7

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.8%	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]	57.3%	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