whatmodel.sh / decision / vLLM-SR Decision 2.0 Sol 2B

vLLM-SR Decision 2.0 Sol 2B

+ contribute

vLLM-SR Decision 2.0 Sol 2B is an open-weights decision model from vLLM Semantic Router. Its published size is 2.27B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine decision-2.0-sol-2b; reported model vLLM-SR Decision 2.0 Sol 2B. 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:sol, manifest 85d3edf9e8bcf7cb39f0907c504781fd2f57a6c0725a24aa4f202dbe103f28a9, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (11027 MiB, rounded upward to 10.8 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.

38.3±1.0#270 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 Sol 2B, out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM	released
270	EXAONE-4.0-1.2B-JEV v0.3 carrtesy	39±1	model files		2026-10-04
271	Von 1.3 (JevBench mini) wfzyx	39±2	source code
272	vLLM-SR Decision 2.0 Sol 2B vLLM Semantic Router	38±1	local	~11GB
273	Sieve 0.8B Sthānika AI	38±1	model files		2026-10-13
274	Amber 0.4B MLukauskas	37±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▁▃▁▁▁▂▃▄▆██▆ #200 of 250 · 7.7% of its score · 6 tests

Beats Cam1, mini-jev Qwen3-4B (decision readout) here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Crivo-68M 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	82.2% ✎	▁▂▁▁▁▃▂▄▅▆█▁ beats 49/246	very easy · avg 92%	▇▇ 3.8%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	67.9% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 86/236	easy · avg 70%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	51.7% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 44/246	easy · avg 72%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	62.0% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 88/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 43/243	medium · avg 37%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	73.4% ✎	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▁▁▁·▁▁▁▃▃▃█▅ #214 of 258 · 4.2% of its score · 7 tests

Beats openvons Qwen3-4B (decision readout), Intelif Qwen3-4B, mini-jev Qwen3-4B (decision readout) here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Mola-68M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	33.8% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 43/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	39.2% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 96/246	medium · avg 38%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	78.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 60/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	78.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 137/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 43/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	78.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 76/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	62.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #207 of 256 · 20% of its score · 9 tests

Beats Valen-2B, Saina Helm 2 Omni (0.8B) here, though they rank higher overall. Trails DecisionTune 1.0, vera-spark, JEV FLAN-T5 Large public v2 (342M) 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	63.3% ✎	▂▄▂▃▄▇▃▇█▅▃▁ beats 49/246	very easy · avg 85%	▇▇▇ 7.6%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	68.5% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 70/246	easy · avg 74%	▇▇ 4.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	44.4% ✎	▁▂▃▅▅█▂····▁ beats 46/246	medium · avg 60%	▇ 3.6%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	23.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 29/246	medium · avg 44%	▇ 1.2%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	60.5% ✎	▁▁▁▁▁▁▁▃▂▇▇█ beats 50/246	easy · avg 71%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	61.0% ✎	▁···▁▁▁▃▃▆█▃ beats 23/246	easy · avg 84%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	45.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 59/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	10.2% ✎	▁▁▁▁▁▃▁▁▁▃▆█ beats 12/246	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: ACOS (per-review F1) submitted	10.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 57/246	hard · avg 22%	▇ 0.4%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #192 of 247 · 6.4% of its score · 6 tests

Beats Kev 9B v2, vLLM-SR d3-nano (2B), Valen-4B here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Bekko System One v0 68M, Crivo-17M 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	46.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 54/246	medium · avg 61%	▇ 2.8%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	61.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 55/246	easy · avg 83%	▇ 1.4%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	55.3% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 61/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	56.7% ✎	▁········▁▇█ beats 64/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	38.1% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 43/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 23/237	hard · avg 21%	▇ 0.2%	sharp · noisy

knowledge & reasoning▁▂▂▂▃▃▃▅▅▆█▂ #201 of 263 · 45% of its score · 19 tests

Beats GLiClass v4 edge (0.4B), Crivo-1B, vLLM-SR vela3-fast (Vela 3.0, 0.4B) here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, Sieve 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	74.0% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 61/246	very easy · avg 90%	▇▇▇ 7.7%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	91.4% ✎	▁▁▂▁▂▂▃▂▃▆█▅ beats 72/246	very easy · avg 96%	▇▇▇ 6.3%	sharp · noisy
Decision Index 0.4.1: MMLU (accuracy) submitted	50.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 57/246	easy · avg 70%	▇▇ 6.0%	sharp · at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	25.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 52/246	medium · avg 46%	▇▇ 5.4%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	49.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 62/246	easy · avg 66%	▇▇ 4.8%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	70.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 84/246	easy · avg 78%	▇ 2.9%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	36.5% ✎	▁··▄█▆▆▆▅▅▃▁ beats 98/246	medium · avg 45%	▇ 1.7%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	31.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 64/246	medium · avg 39%	▇ 1.7%	blunt · at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	62.4% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 8/25	easy · avg 69%	▇ 1.7%	at its level
Ollaya · BoolQ	77.3% ✎	▁··▃▃▁▄▁▃█▇▄ beats 6/25	easy · avg 84%	▇ 1.5%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	56.1% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 82/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	59.0% ✎	▁███▆▅▃▃▁▁▁▁ beats 61/246	easy · avg 71%	▇ 0.7%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	37.4% ✎	██▄▃▃▄▁▁···▁ beats 37/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Ollaya · SQuAD 2 answerability	68.6% ✎	▁▁▃▃▇█▃▃▄▃·▁ beats 4/25	easy · avg 80%	▇ 0.7%	blunt · at its level
Ollaya · VitaminC verification	74.5% ✎	▁···▃·▄█▃··▁ beats 7/25	easy · avg 78%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	13.0% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 52/246	hard · avg 22%	▇ 0.5%	typical
Ollaya · MultiNLI	90.3% ✎	▂··▄██▂▆▆█▆▂ beats 19/25	very easy · avg 87%	▇ 0.4%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	6.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 1/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 80/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▃▆█▄▁▁ #80 of 114 · 11% of its score · 9 tests

Beats vLLM-SR d3-lite (0.8B), Qwen3-Reranker-4B (DecisionBench 22e68366), Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326) here, though they rank higher overall. Trails InternLM Intern-Decision Qwen3.5-2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	55.5% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 9/22	medium · avg 64%	▇ 2.5%	at its level
Ollaya · MASSIVE German intent	75.4% ✎	▁····▁·▂▃▆█▃ beats 7/23	easy · avg 84%	▇ 1.9%	sharp · at its level
Ollaya · PAWS paraphrase	63.6% ✎	▂▂▃▂·▃█▆·▂·▁ beats 4/25	easy · avg 81%	▇ 1.9%	at its level
Ollaya · Aegis 2 safety	73.6% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 10/25	easy · avg 77%	▇ 1.5%	at its level
Ollaya · SummEval relevance	25.8% ✎	▁··▁▂▁▅··▃██ beats 8/25	medium · avg 41%	▇ 1.1%	at its level
Ollaya · MASSIVE English intent	76.9% ✎	▁·······▂▃█▃ beats 4/23	very easy · avg 86%	▇ 0.9%	noisy
Ollaya · SummEval consistency	73.6% ✎	▁·▁▁··▁▁▁▁▄█ beats 8/25	easy · avg 75%	▇ 0.9%	sharp · at its level · noisy
Ollaya · HelpSteer 2 scoring	39.4% ✎	▁▁··▁·▁▃▇█▅▄ beats 15/23	medium · avg 38%	▇ 0.4%	blunt · at its level

1 more test

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Civil Comments	80.0% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 4/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 5.1% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	28.5400 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 61/247	avg 41.206 points	▇ 3.3%	blunt
Decision Index 0.4.1: private new domains (equated points)	16.3000 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 62/247	avg 38.861 points	▇ 1.8%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 10.8 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run decision2:sol --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		▇ 0%
weighted average		= 38.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	73.4%	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]	62.0%	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