whatmodel.sh / decision / RSI-Jev v6.1 VL 4B

RSI-Jev v6.1 VL 4B

+ contribute

RSI-Jev v6.1 VL 4B is an open-weights decision model from shgao, released 7 October 2026. Its published size is 4.66B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine rsi-jev-v6.1-vl-4b; reported model RSI-Jev v6.1 VL 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

Release date ↗ · Weights licence ↗ · Parameter count ↗

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

53.3±1.2#179 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of RSI-Jev v6.1 VL 4B, out of 357 with a score, then more from shgao.

#	model	score	where	released
179	Saif 4B Gyr Technology	54±1	model files
180	SemIf (DecisionBench 1f2dea3e) TheoLeeCJ	54±2	source code
181	RSI-Jev v6.1 VL 4B shgao	53±1	model files	2026-10-07
182	PurpleMIST-Flash-1.0 Olaverse Lab	53±1	model files
183	JevAny-Qwen-4B (direct token) (JevBench mini) SimpleJev	53±2	source code
	more from shgao
51	RSI-Jev v6.1 VL 27B (effort auto) shgao	66±1	model files	2026-10-08
228	RSI-Jev v5.0 VL 3B shgao	48±1	model files	2026-10

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #148 of 250 · 6.9% 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, Amber 0.4B, Gevva E4B 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	71.1% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 93/236	easy · avg 70%	▇ 2.1%	sharp · at its level · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	92.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 100/246	very easy · avg 92%	▇ 1.9%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	44.3% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 124/243	medium · avg 37%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	81.1% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 149/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	63.6% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 110/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.0% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #126 of 258 · 5.7% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Quyet-1.0-Large, Tern-35B-A3B here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-0.8b, Kas 4B 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	41.8% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 114/246	medium · avg 38%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	53.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 128/246	medium · avg 47%	▇ 1.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	73.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 113/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	74.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 146/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	86.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 89/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	80.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 99/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	66.9% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #120 of 256 · 21% of its score · 9 tests

Beats garum (Gemma 4 31B), Shisa DE-2.1 (repeat), garas (Gemma 4 31B) here, though they rank higher overall. Trails Decider 4B, jiwo 4B v2 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	91.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 134/246	very easy · avg 85%	▇▇ 5.1%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	78.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 133/246	easy · avg 74%	▇▇ 4.8%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	67.8% ✎	▁▂▃▅▅█▂····▁ beats 142/246	medium · avg 60%	▇▇ 4.7%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	39.8% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 90/246	medium · avg 44%	▇ 2.0%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	17.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 95/246	hard · avg 22%	▇ 1.0%	noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	76.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 132/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	76.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 178/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	73.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 117/246	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	87.5% ✎	▁···▁▁▁▁▃▆█▃ beats 117/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #99 of 247 · 8.2% of its score · 6 tests

Beats Jev 1.13, Jeffan-4B-2010, Bobcat 1.3 (31B) 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	64.8% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 126/246	medium · avg 61%	▇ 3.5%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.2% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 157/246	medium · avg 60%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	90.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 149/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.4% ✎	▁········▁▇█ beats 155/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	56.2% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 172/237	hard · avg 21%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	53.8% ✎	▁▂▄█▇▅▃▁▄▄▁▁ beats 183/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #158 of 263 · 40% of its score · 14 tests

Beats StartLux-Decision v1.1 2B, Solomon v1.1, Standard One 3B SH (v4) here, though they rank higher overall. Trails Saracura PT-BR 4B, Ryotide Qwen v0.3.1 (decision readout), Interfaze lev Qwen3.5-4B LoRA 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	46.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 102/246	medium · avg 46%	▇▇▇▇ 9.0%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	71.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 101/246	easy · avg 70%	▇▇▇ 6.4%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	69.1% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 128/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	91.4% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 100/246	very easy · avg 90%	▇▇ 3.9%	sharp · maxed out
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	39.2% ✎	▁··▄█▆▆▆▅▅▃▁ beats 107/246	medium · avg 45%	▇ 3.0%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	78.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 123/246	easy · avg 78%	▇ 2.9%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	40.8% ✎	▂▆▅▅▆█▆▃▁··▁ beats 115/246	medium · avg 39%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	96.6% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 98/246	very easy · avg 96%	▇ 2.1%	sharp · maxed out · noisy

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	32.3% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 175/246	hard · avg 22%	▇ 1.1%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	59.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 124/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	53.0% ✎	██▄▃▃▄▁▁···▁ beats 121/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	70.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 126/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	19.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 165/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 62/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #53 of 79 · 11% of its score · 12 tests

Trails JPT-4B Qwen3.5-4B LoRA, LiquidAI d1-3B, Aplomb 1 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	59.3000 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 11/61	avg 63.423 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	24.0200 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 17/61	avg 22.797 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	76.5000 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 21/61	avg 66.987 points	▇ 1.1%	blunt
Decision Index Vision 0.4: private same skills (points)	51.8300 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 23/61	avg 48.067 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	35.7000 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 27/61	avg 28.443 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	56.4400 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 22/61	avg 53.651 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	69.6700 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 26/61	avg 62.137 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	92.3500 points ✎	▁·▁▂▁▁▃▁▂▃▅█ beats 31/61	avg 83.859 points	▇ 0.7%	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	18.9700 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 21/61	avg 19.676 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	50.0600 points ✎	▁···▁▂▂▃█▄▂▃ beats 17/61	avg 44.994 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	72.8000 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 22/61	avg 67.662 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	86.0400 points ✎	▁··▁▁▁▁▁▃▄█▁ beats 10/61	avg 85.184 points	▇ 0.4%	blunt

other tests2 not in a task · 7.1% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	47.4900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 131/247	avg 41.206 points	▇▇ 4.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	39.4600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 123/247	avg 38.861 points	▇ 2.5%	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/shgao ↗

$ how the score was worked out · Decision Index 0.4.1 89%, Decision Index Vision 0.4 11%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇ 11%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 53.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.0%	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]	66.9%	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