whatmodel.sh / decision / Jev-Style 2B v4

Jev-Style 2B v4

+ contribute

Jev-Style 2B v4 is an open-weights decision model from chaoliangUNSW. Its published size is 2.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine jev-style-2b-v4; reported model Jev-Style 2B v4. 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.

46.8±1.1#231 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Jev-Style 2B v4, out of 357 with a score, then more from chaoliangUNSW.

#	model	score	where	released
231	Ryotide Qwen v0.3.1 (decision readout) csabag	47±1	source code
232	decider-2b v10 (JevBench mini) Mapika	47±2	source code
233	Jev-Style 2B v4 chaoliangUNSW	47±1	model files
234	Saracura PT-BR 4B Felhen	46±1	model files
235	LatentMesh Blitz 2B v1 LatentMesh Labs	46±1	request access
	more from chaoliangUNSW
321	Jev-Style 0.8B v3 chaoliangUNSW	28±1	model files	2026-09-24

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #153 of 250 · 7.6% of its score · 6 tests

Beats Cerno 4B v1.1, Trio-Spark DI (9B), Decider 35B-A3B here, though they rank higher overall. Trails JevK5 Lite, Gevva E2B, 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: BFCL (case exact accuracy) submitted	92.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 95/246	very easy · avg 92%	▇ 2.8%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	66.5% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 84/236	easy · avg 70%	▇ 2.3%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	87.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 191/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	62.6% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 95/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	6.8% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 60/243	medium · avg 37%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	77.2% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #87 of 258 · 5.2% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Jev 1.13 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	42.5% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 122/246	medium · avg 38%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.6% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 162/246	medium · avg 47%	▇ 1.7%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	85.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 191/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	77.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 160/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	94.2% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 195/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	87.7% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 159/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	46.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #165 of 256 · 22% 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, vLLM-SR d3-lite (0.8B) 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	81.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 91/246	very easy · avg 85%	▇▇▇ 6.6%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	69.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 77/246	easy · avg 74%	▇▇ 4.9%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	50.1% ✎	▁▂▃▅▅█▂····▁ beats 69/246	medium · avg 60%	▇▇ 4.4%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	47.0% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 119/246	medium · avg 44%	▇ 1.7%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	83.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 202/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	43.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 48/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	9.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 50/246	hard · avg 22%	▇ 0.7%	noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	79.8% ✎	▁···▁▁▁▁▃▆█▃ beats 67/246	easy · avg 84%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	70.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 97/246	easy · avg 66%	▇ 0.7%	at its level · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #169 of 247 · 7.7% of its score · 6 tests

Beats PurpleMIST-Flash-1.0, vLLM-SR Decision 2.0 Nox 4B, Sieve 9B here, though they rank higher overall. Trails Crivo-17M, Crivo-32M v2, Crivo-68M 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	64.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 125/246	medium · avg 61%	▇ 3.4%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 130/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	76.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 77/246	easy · avg 83%	▇ 1.3%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.3% ✎	▁········▁▇█ beats 152/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 41/237	hard · avg 21%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 78/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #183 of 263 · 42% of its score · 14 tests

Beats baselabs joey-1 (2B), Aurelis-2B, StartLux-Decision v1.1 0.8B here, though they rank higher overall. Trails mini-jev Qwen3-4B (decision readout), Gevva E4B, Cam1 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	33.3% ✎	▄▄▃▃▃▄▅▇██▅▁ beats 70/246	medium · avg 46%	▇▇▇ 7.8%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	60.8% ✎	▁▄▄▃▃▃▅▇▅█▇▁ beats 76/246	easy · avg 70%	▇▇▇ 6.7%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	85.8% ✎	▂▂▂▂▂▂▃▃▄▆█▆ beats 78/246	very easy · avg 90%	▇▇ 5.8%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	63.0% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 96/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	94.3% ✎	▁▁▂▁▂▂▂▃▃▆█▅ beats 80/246	very easy · avg 96%	▇ 3.6%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	76.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 115/246	easy · avg 78%	▇ 3.1%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	30.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 81/246	medium · avg 45%	▇ 2.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	35.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 83/246	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	54.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 65/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	29.3% ✎	██▄▃▃▄▁▁···▁ beats 0/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	22.2% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 85/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: CLadder (accuracy) submitted	72.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 138/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	15.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 116/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	12.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 128/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #63 of 79 · 9.4% of its score · 12 tests

Beats djev diffgemma (decision readout), StartLux-Decision v1.1 0.8B, mmastrac diffgemma (decision readout) here, though they rank higher overall. Trails TokenRhythm NeoHorse-Jev-4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	56.4200 points ✎	▁·▁▁▃▃▄▄▃▅█▂ beats 10/61	avg 63.423 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	15.9300 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 12/61	avg 22.797 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	69.5000 points ✎	▁·▁▁▁▁·▂▃▃▅█ beats 17/61	avg 66.987 points	▇ 1.0%	blunt
Decision Index Vision 0.4: private same skills (points)	46.3400 points ✎	▁▁▃▃▁▃▄▆▃▃▅█ beats 15/61	avg 48.067 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	20.8600 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 10/61	avg 28.443 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	54.5000 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 18/61	avg 53.651 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	66.6700 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 21/61	avg 62.137 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	84.7000 points ✎	▁·▁▂▁▁▃▃▂▂▅█ beats 19/61	avg 83.859 points	▇ 0.6%	blunt

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	16.6200 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 15/61	avg 19.676 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	41.2000 points ✎	▁···▁▂▃▂█▄▂▃ beats 11/61	avg 44.994 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	67.9500 points ✎	▁▁▁▁▂▁▃▁▄█▃▃ beats 14/61	avg 67.662 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	87.0400 points ✎	▁··▁▁▁▁▁▃▄█▁ beats 13/61	avg 85.184 points	▇ 0.3%	blunt

other tests2 not in a task · 6.4% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	41.3000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 104/247	avg 41.206 points	▇▇ 4.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	24.3700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 82/247	avg 38.861 points	▇ 2.3%	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/chaoliangUNSW ↗

$ how the score was worked out · Decision Index 0.4.1 90%, Decision Index Vision 0.4 9%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇ 9%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 46.8

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	77.2%	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]	46.6%	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