Sieve 0.8B

+ contribute

Sieve 0.8B is an open-weights decision model from Sthānika AI, released 13 October 2026. Its published size is 0.59B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine sieve-0.8b; reported model Sieve 0.8B. 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

Release date ↗ · Weights licence ↗ · Parameter count ↗

Publisher parameter count (estimated by publisher); includes the served backbone, not just adapter size.

37.7±1.1#271 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Sieve 0.8B, out of 357 with a score, then more from Sthānika AI.

#	model	score	where	RAM	released
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
275	kev-0.6b (DecisionBench dece6dba) Jared Palmer	37±2	model files
	more from Sthānika AI
3	Sieve 31B v3 Sthānika AI	74±2	model files		2026-10-27
37	Sieve 27B v2 Sthānika AI	67±1	model files		2026-10-18
79	Sieve-Vision-27B Sthānika AI	63±4	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #193 of 250 · 9.3% of its score · 6 tests

Beats JevK5 v0.3, openvons Qwen3-4B (decision readout), Cam1 here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Dinah-1 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	84.3% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 56/246	very easy · avg 92%	▇▇ 4.6%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	54.9% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 59/236	easy · avg 70%	▇ 2.3%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	71.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 98/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	61.6% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 84/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 15/243	medium · avg 37%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.1% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #191 of 258 · 5.0% of its score · 7 tests

Beats JevK5 9B v0.3.3, Hopper (G) 1.2 Qwen3.5-4B LoRA, Kev 4B r10 here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Mola-68M, Bosun v3.1 1.7B LoRA 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	41.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 67/246	medium · avg 47%	▇ 1.5%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	27.5% ✎	▁▁▁▁▁▁▁▃▂▄▇█ beats 38/246	medium · avg 38%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	90.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 137/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	58.6% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 41/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	92.7% ✎	█▅▅▄▃▂▃▁▁▁·▁ beats 223/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	85.6% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 139/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	41.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #192 of 256 · 24% of its score · 9 tests

Beats Nari Decision 4B v3.2, Solar Decide Flash, TokenRhythm NeoHorse-Jev-4B 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	75.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 64/246	very easy · avg 85%	▇▇▇▇ 9.2%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	62.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 49/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	43.2% ✎	▁▂▃▅▅█▂····▁ beats 44/246	medium · avg 60%	▇▇ 4.3%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	18.3% ✎	▁·▁·▁▁▃▄▅█▇▄ beats 18/246	medium · avg 44%	▇ 1.4%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	74.1% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 106/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	65.2% ✎	▁···▁▁▁▁▃▆█▃ beats 30/246	easy · avg 84%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	37.1% ✎	▁▁▁▃▅▄▄▂▄▆█▄ beats 20/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	49.8% ✎	▁▁▁▁▁▁▁▁▃▃▆█ beats 44/246	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: ACOS (per-review F1) submitted	10.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 58/246	hard · avg 22%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #204 of 247 · 7.6% of its score · 6 tests

Beats Valen-4B, Saracura PT-BR 4B, TokenRhythm NeoHorse-Jev-4B here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Qwen-2.5-1B-RLCD (decision readout) 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	39.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 33/246	medium · avg 61%	▇ 3.3%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	56.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 43/246	easy · avg 83%	▇ 1.6%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	58.3% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 78/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	57.2% ✎	▁········▁▇█ beats 72/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	41.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 83/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 25/237	hard · avg 21%	▇ 0.2%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▂▃▃▃▅▅▆█▂ #205 of 263 · 48% of its score · 14 tests

Beats Crivo-1B, vLLM-SR vela3-fast (Vela 3.0, 0.4B), Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326) here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, Strands Decider 2B (Hobson v21) 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	73.0% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 58/246	very easy · avg 90%	▇▇▇▇ 9.3%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	86.7% ✎	▁▁▂▁▂▃▂▂▃▆█▅ beats 60/246	very easy · avg 96%	▇▇▇ 7.8%	sharp · noisy
Decision Index 0.4.1: MMLU (accuracy) submitted	50.6% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 58/246	easy · avg 70%	▇▇▇ 7.1%	sharp · at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	26.9% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 57/246	medium · avg 46%	▇▇▇ 6.3%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	45.1% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 50/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	64.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 57/246	easy · avg 78%	▇ 3.5%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	36.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 100/246	medium · avg 45%	▇ 2.0%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	36.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 88/246	medium · avg 39%	▇ 2.0%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	55.5% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 75/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	53.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 29/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	33.0% ✎	██▄▃▃▄▁▁···▁ beats 12/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	14.2% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 55/246	hard · avg 22%	▇ 0.6%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	9.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 49/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	13.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 147/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.0% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	25.2600 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 53/247	avg 41.206 points	▇▇ 3.9%	blunt
Decision Index 0.4.1: private new domains (equated points)	14.1700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 51/247	avg 38.861 points	▇ 2.1%	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/sthanika-ai ↗

$ how the score was worked out · Decision Index 0.4.1 100%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 37.7

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.1%	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]	41.0%	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