Sieve 9B v2

+ contribute

Sieve 9B v2 is an open-weights decision model from Sthānika AI, released 13 October 2026. Its published size is 9.65B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine sieve-9b-plus; reported model Sieve 9B v2. Type: LoRA + head; 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; includes the served backbone, not just adapter size.

57.1±1.3#135 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Sieve 9B v2, out of 357 with a score, then more from Sthānika AI.

#	model	score	where	RAM	released
135	Bespoke Nimble 9B v3 Bespoke Labs	58±1	local	~21GB	2026-10-06
136	simplejev-qwen3.6-35b-a3b (DecisionBench 995ad96e) featherless-ai	58±2	model files
137	Sieve 9B v2 Sthānika AI	57±1	model files		2026-10-13
138	Cerno 4B v1.1 apertixai	57±1	model files		2026-10-19
139	jqv (DecisionBench 9216db57) Octalab-Inc	57±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▁▃▁▁▁▂▃▄▆██▆ #105 of 250 · 7.2% of its score · 6 tests

Beats Xor 26B-A4B v1.2, Senova-4B v2, SynACK Decide 26B-A4B v7 here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, mmastrac diffgemma (decision readout) 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	85.8% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 190/236	easy · avg 70%	▇ 2.2%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	95.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 145/246	very easy · avg 92%	▇ 1.7%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	25.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 97/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	80.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 140/246	easy · avg 72%	▇ 1.1%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	67.3% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 189/246	medium · avg 60%	▇ 1.0%	blunt · at its level
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▁▁▁·▁▁▁▁▃▃█▅ #149 of 258 · 6.7% of its score · 7 tests

Beats Quyet-1.0-Large, Decider chat · Qwen3.6-27B (decision readout) here, though they rank higher overall. Trails Amber 0.4B, Saina Helm 2 Omni (0.8B), jdi-ptr14-0.8b 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	45.1% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 153/246	medium · avg 38%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	49.9% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 106/246	medium · avg 47%	▇ 2.3%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	80.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 147/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	84.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 186/245	easy · avg 70%	▇ 0.6%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	91.2% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 144/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	86.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 143/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	43.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #36 of 256 · 23% of its score · 9 tests

Beats Ainvest-Decision-27B v1.0, H2O Lightning 31B v1.1, Turion Jev 31B 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	65.1% ✎	▁▂▃▅▅█▂····▁ beats 129/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	79.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 147/246	easy · avg 74%	▇▇ 5.4%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	96.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 219/246	very easy · avg 85%	▇▇ 4.8%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	54.9% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 159/246	medium · avg 44%	▇ 2.4%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	17.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 93/246	hard · avg 22%	▇ 1.3%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	73.4% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 99/246	easy · avg 71%	▇ 1.1%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	55.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 96/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 177/246	easy · avg 66%	▇ 0.8%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	88.9% ✎	▁···▁▁▁▁▃▆█▃ beats 138/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #124 of 247 · 10% of its score · 6 tests

Beats Bobcat 1.3 (31B), JEV-35B, OneJev1.6-4B here, though they rank higher overall. Trails vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B), Crivo-400M, Amber 0.4B 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	65.9% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 134/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 131/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	88.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 123/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	62.3% ✎	▁········▁▇█ beats 134/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	8.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 95/237	hard · avg 21%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 69/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #109 of 263 · 45% of its score · 14 tests

Beats OneJev1.6-4B, Seb-9B v2, Mica v0.5 4B here, though they rank higher overall. Trails Decider 35B-A3B, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), Solar Decide 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	59.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 152/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	78.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 145/246	easy · avg 70%	▇▇▇ 6.9%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	70.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 134/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	68.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 183/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	95.4% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 147/246	very easy · avg 90%	▇ 3.5%	sharp · maxed out
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	46.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 163/246	medium · avg 39%	▇ 3.3%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	90.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 202/246	easy · avg 78%	▇ 3.1%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 136/246	very easy · avg 96%	▇ 1.7%	sharp · maxed out · noisy

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	27.9% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 125/246	hard · avg 22%	▇ 1.5%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	56.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 80/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	59.0% ✎	██▄▃▃▄▁▁···▁ beats 140/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	66.9% ✎	▁███▆▅▃▃▁▁▁▁ beats 112/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	12.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 91/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	10.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 30/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 8.6% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	48.8100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 139/247	avg 41.206 points	▇▇ 5.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	44.2900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 140/247	avg 38.861 points	▇ 3.1%	blunt

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. 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 99%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 57.1

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]	43.8%	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