whatmodel.sh / decision / StartLux-Decision v1.1 4B

StartLux-Decision v1.1 4B

+ contribute

StartLux-Decision v1.1 4B is an open-weights decision model from StartLux. Its published size is 4.66B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine startlux-decision-v1.1-4b-instant; reported model StartLux-Decision v1.1 4B. 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.

65.3±1.3#54 of 355 decision modelsfrom 50 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of StartLux-Decision v1.1 4B, out of 357 with a score, then more from StartLux.

#	model	score	where
52	KnowLine 9B Gen1 PelaAI	66±1	model files
53	Herbert v0.5 leinenterprises	65±4	model files
54	StartLux-Decision v1.1 4B StartLux	65±1	model files
55	Quyet-1.0-Large chinhnc	65±1	model files
56	Mercury Decide (paid endpoint) Inception	65±1	api price unknown
	more from StartLux
7	StartLux-Decision v1.1 27B StartLux	73±1	model files
29	StartLux-Decision v1.1 9B StartLux	68±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▁▃▁▁▁▂▃▄▆██▆ #83 of 250 · 5.2% of its score · 6 tests

Beats Sieve 27B v2, Jev 1.13, Span-02 (Gemma 4 26B-A4B) here, though they rank higher overall. Trails Jev-Omni, baselabs joey-1 (2B), Hopper 12B (trained) 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	87.0% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 209/236	easy · avg 70%	▇ 1.5%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	67.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 196/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	95.5% ✎	█▁▁▃▄▄▆▄▁▃▁▃ beats 215/243	medium · avg 37%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 160/246	very easy · avg 92%	▇ 0.9%	sharp · maxed out · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	92.8% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 243/246	easy · avg 72%	▇ 0.8%	noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	80.0% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #12 of 258 · 6.5% 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	47.8% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 194/246	medium · avg 38%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	62.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 235/246	medium · avg 47%	▇ 2.3%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	89.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 235/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	90.5% ✎	█▅▅▄▃▃▁▁▁▁·▁ beats 214/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.7% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 192/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	93.5% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 185/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	54.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #58 of 256 · 19% of its score · 9 tests

Beats Ainvest-Decision-27B v1.0, Turion Jev 31B, MISA AI 2.0 Decision Plus · oak 1.1 (31B) here, though they rank higher overall. Trails Decider 35B-A3B, Sieve 9B v2, Clef-flash 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	74.7% ✎	▁▂▃▅▅█▂····▁ beats 193/246	medium · avg 60%	▇▇ 4.7%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	81.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 162/246	easy · avg 74%	▇▇ 4.5%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	94.8% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 192/246	very easy · avg 85%	▇ 2.7%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	61.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 194/246	medium · avg 44%	▇ 2.4%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	63.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 236/246	hard · avg 22%	▇ 1.5%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	78.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 206/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	85.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 233/246	easy · avg 71%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	84.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 223/246	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	95.4% ✎	▁···▁▁▁▁▃▆█▃ beats 238/246	easy · avg 84%	▇ 0.4%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #38 of 247 · 8.8% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), Nace.AI Drex Max v1 (27B) here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Xor 1.2 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	75.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 194/246	medium · avg 61%	▇ 3.5%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	65.1% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 207/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	80.3% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 220/237	hard · avg 21%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	69.0% ✎	▁········▁▇█ beats 235/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.9% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 208/246	easy · avg 83%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	63.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 231/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #97 of 263 · 37% of its score · 14 tests

Trails decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), Solar Decide, Clef-flash 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	60.9% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 160/246	medium · avg 46%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	79.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 154/246	easy · avg 70%	▇▇ 5.1%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	85.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 216/246	easy · avg 66%	▇▇ 5.1%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	44.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 145/246	medium · avg 39%	▇ 3.5%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	69.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 186/246	medium · avg 45%	▇ 3.2%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	89.6% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 196/246	easy · avg 78%	▇ 2.4%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	57.8% ✎	▁▁▁▁▁▁▁▂▅█▂▃ beats 242/246	hard · avg 22%	▇ 1.8%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	95.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 146/246	very easy · avg 90%	▇ 1.7%	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	69.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 210/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	64.9% ✎	██▄▃▃▄▁▁···▁ beats 155/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	91.7% ✎	▁███▆▅▃▃▃▁▁▁ beats 225/246	easy · avg 71%	▇ 0.8%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	22.1% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 190/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 179/246	very easy · avg 96%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	10.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 55/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #37 of 79 * · 1.4% of its score · 1 test

Beats RSI-Jev v6.1 VL 27B (effort auto) here, though they rank higher overall. Trails Clef-flash, Xor 1.2, OneJev1.5-9B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: VisualDecisionBench images	83.1% ✎	▄▄···█▄·█▄█▄ beats 7/10	easy · avg 78%	▇ 1.4%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #6 of 114 · 8.4% 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), Quyet-1.0-Large here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: Procedural Typed Decisions	87.5% ✎	█·███▄·▄▄▄·▄ beats 10/12	easy · avg 67%	▇▇ 4.7%	sharp
JevalKit: DecisionBench standard eval	81.1% ✎	▃▃·▃···▅█▅·█ beats 10/12	easy · avg 70%	▇ 2.3%	typical
JevalKit: JevBench public 231	88.7% ✎	█▄▄▄▄▄██▄··▄ beats 9/12	easy · avg 82%	▇ 1.3%	typical
JevalKit: Typed Decisions held-out modal labels	78.8% ✎	▃▅··▃·▃▃·█▃█ beats 8/12	easy · avg 74%	▇ 0.2%	blunt

other tests5 not in a task · 13% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	58.2200 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 195/247	avg 41.206 points	▇▇ 5.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	49.6700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 156/247	avg 38.861 points	▇ 3.2%	blunt
JevalKit: JevAlt-Bench EN/TR/DE	92.8% ✎	▅··▃▃▅▃█··▅▃ beats 10/12	very easy · avg 87%	▇ 2.7%	maxed out
JevalKit: Decision Index public 0.3 (official weighted points)	67.8600 points ✎	▃▃·▃·▃▃▃▅▅·█ beats 10/12	avg 39.649 points	▇ 1.3%	blunt
JevalKit: Chinese decision validation v0.2	89.1% ✎	▃····█·█▃▃█▃ beats 5/12	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		= 65.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	80.0%	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]	54.8%	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