Sieve 9B

+ contribute

Sieve 9B 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; reported model Sieve 9B. 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.

50.0±1.2#206 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

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

#	model	score	where	released
206	JevK5 v0.3 alibiserikbay	50±1	model files
207	Span-01 Pro Respan	50±9	api price unknown	2026-09-24
208	Sieve 9B Sthānika AI	50±1	model files	2026-10-13
209	Kev 9B v2 Jared Palmer	50±1	model files	2026-09-30
210	djev diffgemma (decision readout) Davipar	50±1	source code
	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▁▃▁▁▁▂▃▄▆██▆ #115 of 250 · 8.1% of its score · 6 tests

Beats Senova-4B v2, Tern-35B-A3B, GEV-26B-Decide here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, razorback16 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: BFCL (case exact accuracy) submitted	95.4% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 136/246	very easy · avg 92%	▇ 2.6%	sharp · maxed out · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	72.6% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 96/236	easy · avg 70%	▇ 2.5%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	56.1% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 57/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	30.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 107/243	medium · avg 37%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.1% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 139/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.3% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #154 of 258 · 6.0% of its score · 7 tests

Beats Quyet-1.0-Large, Decider chat · Qwen3.6-27B (decision readout), Solar Decide here, though they rank higher overall. Trails DecisionTune 1.0, Amber 0.4B, Saina Helm 2 Omni (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	42.0% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 117/246	medium · avg 38%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	49.3% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 102/246	medium · avg 47%	▇ 2.0%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	63.5% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 72/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	54.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 67/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	76.0% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 52/238	easy · avg 83%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	83.6% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 124/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	62.7% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #155 of 256 · 23% of its score · 9 tests

Beats PurpleMIST-Flash-1.0, Hopper 12B (trained), Jev-Omni here, though they rank higher overall. Trails DecisionTune 1.0, Decider 2B, Crivo-1B 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	83.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 100/246	very easy · avg 85%	▇▇▇ 6.5%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	77.9% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 126/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	56.1% ✎	▁▂▃▅▅█▂····▁ beats 88/246	medium · avg 60%	▇▇ 5.1%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	50.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 136/246	medium · avg 44%	▇ 2.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	61.5% ✎	▁▁▁▁▁▁▁▂▃▇▇█ beats 51/246	easy · avg 71%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	52.2% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 84/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	24.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 137/246	hard · avg 22%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	62.8% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 71/246	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	88.8% ✎	▁···▁▁▁▁▃▆█▃ beats 134/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #185 of 247 · 8.8% of its score · 6 tests

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	58.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 89/246	medium · avg 61%	▇▇ 3.8%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	55.1% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 57/246	medium · avg 60%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	66.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 62/246	easy · avg 83%	▇ 1.3%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	58.0% ✎	▁········▁▇█ beats 78/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	12.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 110/237	hard · avg 21%	▇ 0.6%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 72/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #140 of 263 · 46% of its score · 14 tests

Beats Winnow-12B (DecisionBench b6ac22b0), Amber Hybrid 4B (decision readout), StartLux-Decision v1.1 2B here, though they rank higher overall. Trails Solar Decide Flash, mmastrac diffgemma (decision readout), djev 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: MMLU-Pro (accuracy) submitted	50.8% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 115/246	medium · avg 46%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	74.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 119/246	easy · avg 70%	▇▇▇ 7.3%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	67.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 115/246	easy · avg 66%	▇▇▇ 6.4%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	93.8% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 122/246	very easy · avg 90%	▇▇ 5.4%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	75.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 111/246	easy · avg 78%	▇ 3.3%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	39.2% ✎	▁··▄█▆▆▆▅▅▃▁ beats 106/246	medium · avg 45%	▇ 3.1%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	97.8% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 115/246	very easy · avg 96%	▇ 3.1%	sharp · maxed out · noisy
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	42.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 132/246	medium · avg 39%	▇ 2.8%	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	56.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 94/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	29.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 139/246	hard · avg 22%	▇ 1.1%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	53.7% ✎	██▄▃▃▄▁▁···▁ beats 126/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	63.3% ✎	▁███▆▅▃▃▁▁▁▁ beats 81/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	11.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 77/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	10.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 51/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 7.5% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	42.3000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 112/247	avg 41.206 points	▇▇ 4.8%	blunt
Decision Index 0.4.1: private new domains (equated points)	40.8700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 133/247	avg 38.861 points	▇ 2.6%	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		= 50.0

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.3%	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]	62.7%	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