whatmodel.sh / decision / vLLM-SR Decision 2.0 Eos 0.8B

vLLM-SR Decision 2.0 Eos 0.8B

+ contribute

vLLM-SR Decision 2.0 Eos 0.8B is an open-weights decision model from vLLM Semantic Router. Its published size is 0.87B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine decision-2.0-eos-0.8b; reported model vLLM-SR Decision 2.0 Eos 0.8B. 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:eos, manifest 4c8c10ac75b300337e9687b249e879a19287fc4481f23e5c5e98020eb650733b, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (5909 MiB, rounded upward to 5.8 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.

31.1±1.0#302 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 Eos 0.8B, out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM
302	Bekko System One v0 400M hotchpotch	32±1	model files
303	vera-spark scar-ai	31±1	model files
304	vLLM-SR Decision 2.0 Eos 0.8B vLLM Semantic Router	31±1	local	~5.8GB
305	DecisionTune 1.0 DecisionTune	31±1	model files
306	Together Tev1 Qwen3.5-0.8B Together	31±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▁▃▁▃▁▂▃▄▆██▆ #225 of 250 · 8.2% of its score · 6 tests

Beats DM-JEPA 1.1, Kodiak v0.2 1B (accuracy), JEV FLAN-T5 Large public v2 (342M) here, though they rank higher overall. Trails Prumo (rule-based engine), Crivo-17M, JevK5 Lite 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	57.9% ✎	▁▂▁▃▁▂▂▄▅▆█▁ beats 25/246	very easy · avg 92%	▇▇ 4.8%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	49.6% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 48/236	easy · avg 70%	▇ 1.7%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	40.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 28/246	easy · avg 72%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	59.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 62/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 37/243	medium · avg 37%	▇ 0.2%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	76.5% ✎	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▁▁▁·▁▁▁▃▃▃█▅ #212 of 258 · 3.9% 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	35.0% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 47/246	medium · avg 47%	▇ 1.1%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	27.3% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 37/246	medium · avg 38%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	63.1% ✎	▁▁▁▁▁▁▁▃▃▆█▄ beats 34/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	71.5% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 108/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 24/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	79.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 91/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	60.9% ✎	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▂▂▃▃▂▅▆▃█▆▄▃ #231 of 256 · 20% of its score · 9 tests

Trails JevK5 Lite, LFM2.5-2.6B-RLCD, JEV Ettin 400M 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	43.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 25/246	very easy · avg 85%	▇▇▇ 8.1%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	63.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 56/246	easy · avg 74%	▇▇ 4.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	36.5% ✎	▁▂▃▅▅█▂····▁ beats 28/246	medium · avg 60%	▇ 3.2%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	21.2% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 26/246	medium · avg 44%	▇ 1.0%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	44.5% ✎	▁▁▁▁▁▁▃▂▂▇▇█ beats 28/246	easy · avg 71%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	59.8% ✎	▁···▁▁▁▃▃▆█▃ beats 21/246	easy · avg 84%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	42.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 42/246	medium · avg 62%	▇ 0.6%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	4.5% ✎	▁▁▁▃▁▁▁▁▁▃▆█ beats 8/246	easy · avg 66%	▇ 0.5%	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	7.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 37/246	hard · avg 22%	▇ 0.3%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #219 of 247 · 6.0% of its score · 6 tests

Beats Valen-4B, TokenRhythm NeoHorse-Jev-4B, OneJev1.6-0.8B here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Bekko System One v0 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	40.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 34/246	medium · avg 61%	▇ 2.5%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	51.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 27/246	easy · avg 83%	▇ 1.5%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	54.5% ✎	▁·▁▃▃▂▅█▄▂▁▁ beats 54/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	51.2% ✎	▁········▁▇█ beats 29/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	36.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 25/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	7.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 90/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▃▂▃▃▅▅▆█▂ #225 of 263 · 46% of its score · 19 tests

Beats Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326), Amber 0.4B, vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B) here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), LFM2.5-2.6B-RLCD, InternLM Intern-Decision Qwen3.5-0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	78.0% ✎	▁▁▂▁▃▂▂▂▃▆█▅ beats 40/246	very easy · avg 96%	▇▇▇▇ 10%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	57.0% ✎	▂▂▂▃▂▂▁▃▄▆█▆ beats 36/246	very easy · avg 90%	▇▇▇▇ 8.9%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	39.8% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 32/246	easy · avg 70%	▇▇ 5.5%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	42.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 42/246	easy · avg 66%	▇▇ 4.4%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	18.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 34/246	medium · avg 46%	▇▇ 4.1%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	51.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 17/246	easy · avg 78%	▇ 3.0%	at its level
Ollaya · PubMedQA	53.2% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 6/25	easy · avg 69%	▇ 1.6%	at its level
Ollaya · BoolQ	74.7% ✎	▁··▃▃▃▄▁▃█▇▄ beats 5/25	easy · avg 84%	▇ 1.6%	at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	25.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 22/246	medium · avg 39%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	20.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 42/246	medium · avg 45%	▇ 1.3%	sharp
Decision Index 0.4.1: MuSR (accuracy) submitted	50.0% ✎	▁▁▃█▅▄▁▁▁▁▁▁ beats 32/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Ollaya · SQuAD 2 answerability	76.6% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 12/25	easy · avg 80%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	54.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 39/246	easy · avg 71%	▇ 0.7%	at its level
Ollaya · VitaminC verification	77.1% ✎	▁···▃·▄█▃··▁ beats 15/25	easy · avg 78%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	40.7% ✎	██▄▃▃▄▁▁···▁ beats 63/246	medium · avg 58%	▇ 0.6%	at its level · noisy
Ollaya · MultiNLI	85.3% ✎	▂··▄██▃▆▆█▆▂ beats 11/25	very easy · avg 87%	▇ 0.5%	blunt
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	10.8% ✎	▁▁▁▁▁▁▃▂▅█▂▁ beats 46/246	hard · avg 22%	▇ 0.4%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 34/246	hard · avg 16%	▇ 0.2%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	12.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 109/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▃▂▆█▄▁▁ #85 of 114 · 11% of its score · 9 tests

Beats Qwen3-Reranker-4B (DecisionBench 22e68366), kev-0.6b (DecisionBench dece6dba), mojev (DecisionBench 0c8695b6) here, though they rank higher overall. Trails LiquidAI d1-omni-600M, InternLM Intern-Decision Qwen3.5-0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	46.0% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 4/22	medium · avg 64%	▇ 2.3%	at its level
Ollaya · MASSIVE German intent	72.3% ✎	▁····▁·▂▃▆█▃ beats 5/23	easy · avg 84%	▇ 2.0%	sharp · at its level
Ollaya · PAWS paraphrase	58.4% ✎	▂▃▂▂·▃█▆·▂·▁ beats 3/25	easy · avg 81%	▇ 2.0%	at its level
Ollaya · Aegis 2 safety	72.8% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 9/25	easy · avg 77%	▇ 1.5%	at its level
Ollaya · MASSIVE English intent	74.6% ✎	▁·······▃▃█▃ beats 2/23	very easy · avg 86%	▇ 1.0%	at its level · noisy
Ollaya · SummEval consistency	81.9% ✎	▁·▁▁··▁▁▁▁▄█ beats 15/25	easy · avg 75%	▇ 0.9%	sharp · at its level · noisy
Ollaya · SummEval relevance	15.4% ✎	▁··▁▃▁▅··▃██ beats 2/25	medium · avg 41%	▇ 0.8%	typical
Ollaya · HelpSteer 2 scoring	34.9% ✎	▁▁··▁·▁▃▇█▅▄ beats 9/23	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	82.3% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 6/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 4.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	20.5000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 37/247	avg 41.206 points	▇ 3.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	15.1900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 57/247	avg 38.861 points	▇ 1.7%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 5.8 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run decision2:eos --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 84%, 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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 84%	CC BY 4.0
Ollaya · original runs	14	▇▇▇▇▇ 16%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 31.1

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	76.5%	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]	60.9%	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