JevK5 v0.3

+ contribute

JevK5 v0.3 is an open-weights decision model from alibiserikbay. Its published size is 4.66B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine jevk5-v0.3; reported model JevK5 v0.3. Type: LoRA; 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.

50.3±1.0#204 of 355 decision modelsfrom 59 benchmark results across 4 sources

$ how it compares

The decision models ranked either side of JevK5 v0.3, out of 357 with a score, then more from alibiserikbay.

#	model	score	where	RAM	released
204	JPT-4B Qwen3.5-4B LoRA kirp	50±1	model files
205	Bespoke Nimble 9B v2 Bespoke Labs	50±1	local	~20GB
206	JevK5 v0.3 alibiserikbay	50±1	model files
207	Span-01 Pro Respan	50±9	api price unknown		2026-09-24
208	Sieve 9B Sthānika AI	50±1	model files		2026-10-13
	more from alibiserikbay
167	JevK5 9B v0.3.3 alibiserikbay	54±1	model files
328	JevK5 Lite alibiserikbay	25±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #194 of 250 · 10% of its score · 8 tests

Trails JevK5 Lite, Mola-68M, Dinah-1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecideBench v1: agent routing	96.0% ✎	▄·····▂▄·█·▄ beats 4/10	very easy · avg 93%	▇ 3.2%	sharp · noisy
DecideBench v1: action review	72.0% ✎	▃▃·▃·█···█·▅ beats 2/10	easy · avg 87%	▇ 1.8%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	84.1% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 55/246	very easy · avg 92%	▇ 1.7%	sharp · maxed out · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	60.6% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 72/236	easy · avg 70%	▇ 1.7%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	73.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 107/246	easy · avg 72%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	21.6% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 90/243	medium · avg 37%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	61.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 82/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #189 of 258 · 5.1% of its score · 8 tests

Beats JevK5 9B v0.3.3 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	42.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 120/246	medium · avg 38%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	41.9% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 69/246	medium · avg 47%	▇ 1.4%	at its level
DecideBench v1: support intent	100.0% ✎	▃····▂▂·▃··█ beats 9/10	very easy · avg 95%	▇ 1.0%	sharp · maxed out · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	67.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 92/246	easy · avg 74%	▇ 0.4%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	59.7% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 82/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	76.9% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 56/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	65.0% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 30/238	easy · avg 79%	▇ 0.2%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	57.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #124 of 256 · 24% of its score · 12 tests

Beats garum (Gemma 4 31B), Shisa DE-2.1 (repeat), garas (Gemma 4 31B) here, though they rank higher overall. Trails vLLM-SR d3-nano (2B) 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	90.4% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 131/246	very easy · avg 85%	▇▇ 4.3%	sharp
DecideBench v1: review sentiment	84.0% ✎	▂··▂···▃▂█▄▂ beats 2/10	easy · avg 85%	▇▇ 4.3%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	76.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 107/246	easy · avg 74%	▇ 3.7%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	59.9% ✎	▁▂▃▅▅█▂····▁ beats 106/246	medium · avg 60%	▇ 3.4%	at its level
DecideBench v1: content moderation	82.0% ✎	▂··▂···▄▄▂·█ beats 3/10	easy · avg 83%	▇ 2.7%	sharp · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	51.0% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 138/246	medium · avg 44%	▇ 1.4%	at its level
DecideBench v1: claim support	92.0% ✎	▄··▄·▄·▄▄███ beats 5/10	easy · avg 82%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	66.3% ✎	▁▁▁▁▁▁▁▂▃▇▇█ beats 65/246	easy · avg 71%	▇ 0.7%	at its level · noisy

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: VAST (macro-F1) submitted	41.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 36/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	18.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 99/246	hard · avg 22%	▇ 0.6%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	71.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 103/246	easy · avg 66%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	83.4% ✎	▁···▁▁▁▁▃▆█▃ beats 91/246	easy · avg 84%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #145 of 247 · 6.0% of its score · 6 tests

Beats OneJev1.6-4B, Nace.AI Drex v1.5, Jegue 0.1 (9B) here, though they rank higher overall. Trails Crivo-32M v2, Crivo-68M, Crivo-150M v2 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	62.7% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 119/246	medium · avg 61%	▇ 2.6%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.1% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 150/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	83.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 102/246	easy · avg 83%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	62.8% ✎	▁········▁▇█ beats 138/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	4.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 68/237	hard · avg 21%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	43.2% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 110/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #145 of 263 · 31% of its score · 14 tests

Beats Winnow-12B (DecisionBench b6ac22b0), StartLux-Decision v1.1 2B, Standard One 8B SH (v4) here, though they rank higher overall. Trails razorback16 diffgemma (decision readout), Solar Decide Flash, mmastrac diffgemma (decision readout) 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	51.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 121/246	medium · avg 46%	▇▇▇ 6.4%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	74.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 118/246	easy · avg 70%	▇▇ 4.9%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	64.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 102/246	easy · avg 66%	▇▇ 4.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	93.2% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 113/246	very easy · avg 90%	▇ 3.6%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	74.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 109/246	easy · avg 78%	▇ 2.2%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	32.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 84/246	medium · avg 45%	▇ 2.1%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	97.9% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 125/246	very easy · avg 96%	▇ 2.0%	sharp · maxed out · noisy
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	41.3% ✎	▂▆▅▅▆█▆▃▁··▁ beats 124/246	medium · avg 39%	▇ 1.9%	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	50.8% ✎	▁▁▃█▅▄▁▁▁▁▁▁ beats 35/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	29.8% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 143/246	hard · avg 22%	▇ 0.8%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	44.4% ✎	██▄▃▃▄▁▁···▁ beats 82/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	63.6% ✎	▁███▆▅▃▃▁▁▁▁ beats 86/246	easy · avg 71%	▇ 0.6%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	12.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 84/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	13.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 169/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #54 of 114 · 13% of its score · 6 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecideBench v1: ticket triage	94.0% ✎	▄·····▂█·▆·▂ beats 4/10	very easy · avg 90%	▇▇ 4.4%	sharp
JevalKit: Procedural Typed Decisions	61.5% ✎	█·███▄·▄▄▄·▄ beats 3/12	easy · avg 67%	▇▇ 4.3%	sharp · at its level
JevalKit: DecisionBench standard eval	76.1% ✎	▃▃·▃···▅█▅·█ beats 7/12	easy · avg 70%	▇ 1.8%	at its level
DecideBench v1: returns policy	90.0% ✎	▃··▃··▃·▅▅█▃ beats 6/10	easy · avg 81%	▇ 1.7%	sharp · noisy
JevalKit: JevBench public 231	88.7% ✎	█▄▄▄▄▄██▄··▄ beats 10/12	easy · avg 82%	▇ 1.0%	typical
JevalKit: Typed Decisions held-out modal labels	62.8% ✎	▃▅··▃·▃▃·█▃█ beats 0/12	easy · avg 74%	▇ 0.1%	blunt · at its level

other tests7 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)	41.1800 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 103/247	avg 41.206 points	▇ 3.3%	blunt
JevalKit: JevAlt-Bench EN/TR/DE	87.0% ✎	▅··▃▃▅▃█··▅▃ beats 4/12	very easy · avg 87%	▇ 2.4%	typical
Decision Index 0.4.1: private new domains (equated points)	29.7100 points ✎	▃█▃▃▃▆▃▃▄▄▄▄ beats 95/247	avg 38.861 points	▇ 1.8%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	38.5320 points ✎	▃···▃·▃▃█▅▅█ beats 1/13	avg 32.166 points	▇ 1.4%	blunt
JevalKit: Decision Index public 0.3 (official weighted points)	41.5900 points ✎	▃▃·▃·▃▃▃▅▅·█ beats 4/12	avg 39.649 points	▇ 0.8%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	89.8823 points ✎	▂······▂▆▂██ beats 7/13	avg 70.133 points	▇ 0.4%	blunt
JevalKit: Chinese decision validation v0.2	87.4% ✎	▃····█·█▃▃█▃ beats 2/12	very easy · avg 88%	▇ 0.1%	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/alibiserikbay ↗

$ how the score was worked out · Decision Index 0.4.1 67%, DecideBench (Cho Yin Yong) 20%, JevalKit (Valen Team) 10% and 1 more

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%	CC BY 4.0
DecideBench (Cho Yin Yong)	8	▇▇▇▇▇▇ 20%	CC BY 4.0
JevalKit (Valen Team)	7	▇▇▇ 10%	Apache-2.0
Benchmark Heaven (own decision evaluations)	2	▇ 2%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 50.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.8%	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]	57.6%	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