whatmodel.sh / decision / StartLux-Decision v1.1 0.8B

StartLux-Decision v1.1 0.8B

+ contribute

StartLux-Decision v1.1 0.8B is an open-weights decision model from StartLux. Its published size is 0.87B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine startlux-decision-v1.1-0.8b-instant; reported model StartLux-Decision v1.1 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

· Weights licence ↗ · Parameter count ↗

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

48.5±1.1#218 of 355 decision modelsfrom 50 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of StartLux-Decision v1.1 0.8B, out of 357 with a score, then more from StartLux.

#	model	score	where	RAM	released
218	zerank-2-reranker (DecisionBench 5eae30d5) zeroentropy	49±2	model files
219	Kev 4B r10 Jared Palmer	49±1	local	~11GB	2026-09-24
220	StartLux-Decision v1.1 0.8B StartLux	49±1	model files
221	mmastrac diffgemma (decision readout) vllm-project	48±1	source code
222	InternLM Intern-Decision Qwen3.5-4B Shanghai AI Laboratory (InternLM)	48±1	model files
	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
54	StartLux-Decision v1.1 4B StartLux	65±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #135 of 250 · 7.0% of its score · 6 tests

Beats Cerno 4B v1.1, Trio-Spark DI (9B), Decider 35B-A3B here, though they rank higher overall. Trails Amber 0.4B, OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B 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	93.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 114/246	very easy · avg 92%	▇ 2.4%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	78.3% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 111/236	easy · avg 70%	▇ 2.1%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	85.8% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 176/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	60.2% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 146/243	medium · avg 37%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	64.0% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 117/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	68.5% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #44 of 258 · 5.0% of its score · 7 tests

Beats H2O Lightning 31B v1.1, AutoTrust-JEV-27B v1.1, MISA AI 2.0 Decision Plus · oak 1.1 (31B) 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	41.1% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 108/246	medium · avg 38%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	59.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 207/246	medium · avg 47%	▇ 1.7%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	85.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 184/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	81.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 180/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	90.3% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 133/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.2% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 183/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	65.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #177 of 256 · 20% of its score · 9 tests

Beats Nari Decision 4B v3.2 here, though they rank higher overall. Trails DecisionTune 1.0, jdi-ptr14-0.8b, FLock this-that 1.2 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	78.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 78/246	very easy · avg 85%	▇▇ 5.9%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	67.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 64/246	easy · avg 74%	▇▇ 4.6%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	57.1% ✎	▁▂▃▅▅█▂····▁ beats 96/246	medium · avg 60%	▇▇ 4.3%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	36.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 78/246	medium · avg 44%	▇ 1.7%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	84.4% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 216/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	75.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 176/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	58.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 233/246	hard · avg 22%	▇ 0.7%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	77.5% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 150/246	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: FinEntity (macro-F1) submitted	91.8% ✎	▁···▁▁▁▁▃▆█▃ beats 174/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #104 of 247 · 7.4% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B), decisio 0.6.0 (Gemma 4 31B) (decision readout) 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	60.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 103/246	medium · avg 61%	▇ 3.2%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.3% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 126/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	90.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 140/246	easy · avg 83%	▇ 1.2%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	66.3% ✎	▁········▁▇█ beats 214/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	78.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 207/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	60.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 207/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #195 of 263 · 39% of its score · 14 tests

Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, Sieve 2B 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	33.4% ✎	▄▄▃▃▃▄▅▇██▅▁ beats 71/246	medium · avg 46%	▇▇▇ 7.7%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	55.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 67/246	easy · avg 70%	▇▇▇ 6.3%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	71.5% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 143/246	easy · avg 66%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	78.2% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 66/246	very easy · avg 90%	▇▇ 5.0%	sharp
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	90.7% ✎	▁▁▂▁▂▂▃▂▃▆█▅ beats 70/246	very easy · avg 96%	▇ 3.0%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	70.6% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 89/246	easy · avg 78%	▇ 2.9%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	37.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 102/246	medium · avg 45%	▇ 2.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	30.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 59/246	medium · avg 39%	▇ 2.3%	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	59.7% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 131/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	50.6% ✎	▁▁▁▁▁▁▁▂▅█▂▃ beats 239/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	34.7% ✎	██▄▃▃▄▁▁···▁ beats 25/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	79.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 173/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	21.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 174/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	12.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 137/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▃▃▃▇▄▄█▄▃ #71 of 79 * · 1.3% of its score · 1 test

Trails LiquidAI d1-omni-600M, InternLM Intern-Decision Qwen3.5-2B, Valen-2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: VisualDecisionBench images	70.4% ✎	▄▄···█▄·█▄█▄ beats 1/10	easy · avg 78%	▇ 1.3%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #45 of 114 · 9.1% of its score · 4 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
JevalKit: Procedural Typed Decisions	70.5% ✎	█·███▄·▄▄▄·▄ beats 7/12	easy · avg 67%	▇▇ 5.4%	sharp · at its level
JevalKit: DecisionBench standard eval	74.6% ✎	▃▃·▃···▅█▅·█ beats 5/12	easy · avg 70%	▇ 2.3%	at its level
JevalKit: JevBench public 231	79.7% ✎	█▄▄▄▄▄██▄··▄ beats 4/12	easy · avg 82%	▇ 1.3%	typical
JevalKit: Typed Decisions held-out modal labels	75.4% ✎	▃▅··▃·▃▃·█▃█ beats 5/12	easy · avg 74%	▇ 0.1%	blunt · at its level

other tests5 not in a task · 10% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	40.7100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 100/247	avg 41.206 points	▇▇ 4.0%	blunt
JevalKit: JevAlt-Bench EN/TR/DE	87.7% ✎	▅··▃▃▅▃█··▅▃ beats 5/12	very easy · avg 87%	▇ 3.1%	typical
Decision Index 0.4.1: private new domains (equated points)	11.1200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 26/247	avg 38.861 points	▇ 2.2%	blunt
JevalKit: Decision Index public 0.3 (official weighted points)	53.6200 points ✎	▃▃·▃·▃▃▃▅▅·█ beats 6/12	avg 39.649 points	▇ 0.9%	blunt
JevalKit: Chinese decision validation v0.2	89.1% ✎	▃····█·█▃▃█▃ beats 6/12	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) 15%

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	▇▇▇▇ 15%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 48.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	68.5%	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]	65.6%	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