whatmodel.sh / decision / StartLux-Decision v1.1 9B

StartLux-Decision v1.1 9B

+ contribute

StartLux-Decision v1.1 9B is an open-weights decision model from StartLux. Its published size is 9.65B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine startlux-decision-v1.1-9b-instant; reported model StartLux-Decision v1.1 9B. 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

· Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

68.2±1.4#29 of 355 decision modelsfrom 50 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of StartLux-Decision v1.1 9B, out of 357 with a score, then more from StartLux.

#	model	score	where
27	AJev lm6q (Gemma 4 31B) andyzhang232	69±2	model files
28	AnyJev Tacitus 31B morriszjm	69±2	model files
29	StartLux-Decision v1.1 9B StartLux	68±1	model files
30	OneShot 27B OneShot	68±2	model files
31	Matilda Decision v1 Maincode	68±2	model files
	more from StartLux
7	StartLux-Decision v1.1 27B StartLux	73±1	model files
54	StartLux-Decision v1.1 4B StartLux	65±1	model files
158	StartLux-Decision v1.1 2B StartLux	55±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #28 of 250 · 4.8% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, KnowLine 31B Gen1 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni 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	89.6% ✎	▁▁▁▁▁▁▁▂▃▂█▃ beats 231/236	easy · avg 70%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	67.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 197/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	98.9% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 223/243	medium · avg 37%	▇ 0.8%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	93.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 245/246	easy · avg 72%	▇ 0.8%	noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 216/246	very easy · avg 92%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.6% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #6 of 258 · 6.8% of its score · 7 tests

Beats Fastino GLiDE 1.2, KnowLine 31B Gen1, Ainvest-Decision-27B v1.0 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	46.5% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 172/246	medium · avg 38%	▇ 2.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	63.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 241/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	90.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 242/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	92.3% ✎	█▅▅▄▃▃▁▁▁▁·▁ beats 221/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	93.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 228/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	94.3% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 196/238	easy · avg 83%	▇ 0.2%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	68.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #30 of 256 · 18% of its score · 9 tests

Beats KnowLine 31B Gen1, Ainvest-Decision-27B v1.0, H2O Lightning 31B v1.1 here, though they rank higher overall. Trails Clef-flash, Clef-omni, JEV-35B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	77.0% ✎	▁▂▃▅▅█▂····▁ beats 215/246	medium · avg 60%	▇▇ 4.7%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	84.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 208/246	easy · avg 74%	▇▇ 4.4%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	61.5% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 193/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	96.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 217/246	very easy · avg 85%	▇ 2.3%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	64.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 241/246	hard · avg 22%	▇ 1.7%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	79.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 208/246	medium · avg 62%	▇ 1.0%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	86.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 243/246	easy · avg 71%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	84.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 227/246	easy · avg 66%	▇ 0.6%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	95.7% ✎	▁···▁▁▁▁▃▆█▃ beats 241/246	easy · avg 84%	▇ 0.4%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▃▁▁ #21 of 247 · 9.0% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), WeMM-JEV-27B here, though they rank higher overall. Trails Senova-4B v2, AnyJev L0 · Gemma-4-31B (decision readout), RSI-Jev v6.1 VL 27B (effort auto) 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	80.3% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 223/246	medium · avg 61%	▇ 3.5%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	66.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 219/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	81.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 229/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	69.9% ✎	▁········▁▇█ beats 240/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	97.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 225/246	easy · avg 83%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	65.6% ✎	▁▂▄█▇▅▁▁▄▄▃▁ beats 240/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #80 of 263 · 37% of its score · 14 tests

Trails Solar Decide, Clef-flash, Decider chat · Qwen3.6-27B (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	64.6% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 175/246	medium · avg 46%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	86.9% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 222/246	easy · avg 66%	▇▇ 5.0%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	82.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 161/246	easy · avg 70%	▇▇ 4.9%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	50.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 200/246	medium · avg 39%	▇ 3.7%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	69.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 187/246	medium · avg 45%	▇ 3.2%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	92.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 216/246	easy · avg 78%	▇ 2.3%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	58.2% ✎	▁▁▁▁▁▁▁▂▅█▂▃ beats 243/246	hard · avg 22%	▇ 2.0%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	95.9% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 158/246	very easy · avg 90%	▇ 1.4%	sharp · maxed out

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	70.7% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 221/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	68.8% ✎	██▄▃▃▄▁▁···▁ beats 163/246	medium · avg 58%	▇ 1.0%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	23.6% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 210/246	hard · avg 16%	▇ 0.9%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	92.7% ✎	▁███▆▅▃▃▃▁▁▁ beats 229/246	easy · avg 71%	▇ 0.9%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.8% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 165/246	very easy · avg 96%	▇ 0.5%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	11.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 85/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #33 of 79 * · 1.4% of its score · 1 test

Trails Clef-flash, GPT-6 Luna Decisions, Perplexity Decider Flash v1.2 (4B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: VisualDecisionBench images	84.2% ✎	▄▄···█▄·█▄█▄ beats 8/10	easy · avg 78%	▇ 1.4%	blunt

workflows▁▁▁▂▁▂▂▆█▄▃▁ #4 of 114 · 8.2% of its score · 4 tests

Beats baselabs mammoth-1 (27B), Nace.AI Drex Max v1 (27B), Perplexity Decider v1.2 (27B) here, though they rank higher overall. Trails Mercury Decide (paid endpoint) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: Procedural Typed Decisions	88.8% ✎	█·███▄·▄▄▄·▄ beats 11/12	easy · avg 67%	▇▇ 4.5%	sharp
JevalKit: DecisionBench standard eval	81.9% ✎	▃▃·▃···▅█▅·█ beats 11/12	easy · avg 70%	▇ 2.3%	typical
JevalKit: JevBench public 231	89.6% ✎	█▄▄▄▄▄██▄··▄ beats 11/12	easy · avg 82%	▇ 1.2%	typical
JevalKit: Typed Decisions held-out modal labels	81.3% ✎	▃▅··▃·▃▃·█▃█ beats 12/12	easy · avg 74%	▇ 0.2%	blunt

other tests5 not in a task · 14% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	60.9500 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 211/247	avg 41.206 points	▇▇ 6.2%	blunt
Decision Index 0.4.1: private new domains (equated points)	53.7500 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 166/247	avg 38.861 points	▇ 3.4%	blunt
JevalKit: JevAlt-Bench EN/TR/DE	93.4% ✎	▅··▃▃▅▃█··▅▃ beats 11/12	very easy · avg 87%	▇ 2.6%	maxed out
JevalKit: Decision Index public 0.3 (official weighted points)	69.9200 points ✎	▃▃·▃·▃▃▃▅▅·█ beats 11/12	avg 39.649 points	▇ 1.4%	blunt
JevalKit: Chinese decision validation v0.2	91.0% ✎	▃····█·█▃▃█▃ beats 11/12	very easy · avg 88%	▇ 0.2%	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/startlux-models ↗

$ how the score was worked out · Decision Index 0.4.1 85%, JevalKit (Valen Team) 14%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%	CC BY 4.0
JevalKit (Valen Team)	8	▇▇▇▇ 14%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 68.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.6%	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]	68.4%	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