whatmodel.sh / decision / RSI-Jev v5.0 VL 3B

RSI-Jev v5.0 VL 3B

+ contribute

RSI-Jev v5.0 VL 3B is an open-weights decision model from shgao, released October 2026. Its published size is 4.66B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine rsi-jev-v5.0-vl-3b; reported model RSI-Jev v5.0 VL 3B. 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.

47.5±1.1#226 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of RSI-Jev v5.0 VL 3B, out of 357 with a score, then more from shgao.

#	model	score	where	released
226	Open-Jev-2B (DecisionBench 0c7aa498) ZefanCai	48±2	model files	2026-09-20
227	Valen-4B Valen	48±1	model files
228	RSI-Jev v5.0 VL 3B shgao	48±1	model files	2026-10
229	Sieve 2B v3 Sthānika AI	48±1	model files
230	Lev1 3.7B theaviv	47±1	model files	2026-10-04
	more from shgao
51	RSI-Jev v6.1 VL 27B (effort auto) shgao	66±1	model files	2026-10-08
181	RSI-Jev v6.1 VL 4B shgao	53±1	model files	2026-10-07

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #189 of 250 · 7.5% of its score · 6 tests

Beats JevK5 v0.3, FlyMy.AI Decision 4B v1.6 here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Mola-150M 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	85.8% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 60/246	very easy · avg 92%	▇ 2.7%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	55.3% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 61/236	easy · avg 70%	▇ 2.3%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	57.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 61/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	62.6% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 94/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	22.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 92/243	medium · avg 37%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	74.9% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #198 of 258 · 5.2% of its score · 7 tests

Beats Hopper (G) 1.2 Qwen3.5-4B LoRA, Solar Decide Flash here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Mola-68M, Bosun v3.1 1.7B LoRA 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	40.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 99/246	medium · avg 38%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	39.9% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 60/246	medium · avg 47%	▇ 1.7%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	62.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 64/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	63.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 101/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	76.0% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 51/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	66.2% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 34/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	64.1% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #136 of 256 · 21% of its score · 9 tests

Beats Solar Decide, Winnow-12B, JoshuaSP diffgemma (decision readout) here, though they rank higher overall. Trails Sieve 2B v3 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	86.8% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 118/246	very easy · avg 85%	▇▇▇ 6.4%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	77.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 117/246	easy · avg 74%	▇▇ 4.9%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	65.3% ✎	▁▂▃▅▅█▂····▁ beats 130/246	medium · avg 60%	▇▇ 4.5%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	31.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 65/246	medium · avg 44%	▇ 1.7%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	72.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 86/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	50.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 78/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	10.8% ✎	▁··▂▃▃▅▇█▇▃▃ beats 62/246	hard · avg 22%	▇ 0.7%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	61.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 69/246	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	89.9% ✎	▁···▁▁▁▁▃▆█▃ beats 147/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #194 of 247 · 7.8% of its score · 6 tests

Beats Kev 9B v2, vLLM-SR d3-nano (2B), Valen-4B here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Bekko System One v0 68M, Crivo-17M 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	54.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 69/246	medium · avg 61%	▇ 3.4%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	56.7% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 66/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	60.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 52/246	easy · avg 83%	▇ 1.3%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.6% ✎	▁········▁▇█ beats 157/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	7.2% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 88/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	38.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 47/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #168 of 263 · 41% of its score · 14 tests

Beats Solomon v1.1, Standard One 3B SH (v4), baselabs joey-1 (2B) here, though they rank higher overall. Trails Jevstral 8B, Jobe Qwen3.5-4B (decision readout), Metask-Jev-4B 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	43.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 90/246	medium · avg 46%	▇▇▇ 8.0%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	69.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 95/246	easy · avg 70%	▇▇▇ 6.7%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	62.5% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 91/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	89.0% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 91/246	very easy · avg 90%	▇▇ 5.6%	sharp
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	96.7% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 100/246	very easy · avg 96%	▇ 3.4%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	70.0% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 83/246	easy · avg 78%	▇ 3.0%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	29.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 80/246	medium · avg 45%	▇ 2.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	36.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 86/246	medium · avg 39%	▇ 2.4%	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	59.3% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 125/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	42.3% ✎	██▄▃▃▄▁▁···▁ beats 70/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	30.7% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 153/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: CLadder (accuracy) submitted	66.8% ✎	▁███▆▅▃▃▁▁▁▁ beats 109/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	10.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 57/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	9.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 22/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #57 of 79 · 10% of its score · 12 tests

Beats QEV-2B, Shisa DE-2 (repeat), djev diffgemma (decision readout) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	63.6900 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 15/61	avg 63.423 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	25.0800 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 18/61	avg 22.797 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	77.0000 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 22/61	avg 66.987 points	▇ 1.0%	blunt
Decision Index Vision 0.4: private same skills (points)	52.1000 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 27/61	avg 48.067 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	42.4600 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 41/61	avg 28.443 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	55.8800 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 20/61	avg 53.651 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	66.6700 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 20/61	avg 62.137 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	82.5100 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 14/61	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	11.7500 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 6/61	avg 19.676 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	50.7000 points ✎	▁···▁▂▂▃█▄▂▃ beats 19/61	avg 44.994 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	72.9600 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 23/61	avg 67.662 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	86.1700 points ✎	▁··▁▁▁▁▁▃▄█▁ beats 11/61	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)	38.0800 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 87/247	avg 41.206 points	▇▇ 4.2%	blunt
Decision Index 0.4.1: private new domains (equated points)	39.5100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 124/247	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/shgao ↗

$ how the score was worked out · Decision Index 0.4.1 90%, Decision Index Vision 0.4 10%

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	▇▇▇ 10%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 47.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	74.9%	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]	64.1%	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