jiwo 4B v2

+ contribute

jiwo 4B v2 is an open-weights decision model from eljiwo, released 9 October 2026. Its published size is 4.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine jiwo-4b-v2; reported model jiwo 4B v2. 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.

52.3±1.2#187 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of jiwo 4B v2, out of 357 with a score, then more from eljiwo.

#	model	score	where	released
187	Hopper 12B (trained) HopitAI	52±1	model files
188	Jebadiah 9B v2 (JevBench mini) Frontier Infra	52±2	source code
189	jiwo 4B v2 eljiwo	52±1	model files	2026-10-09
190	baselabs joey-1 (2B) baselabs	52±1	api price unknown
191	QEV-2B ken-jo	52±4	model files
	more from eljiwo
276	jiwo 0.8B v2 eljiwo	37±1	model files	2026-10-10

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #145 of 250 · 7.8% 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, Crivo-1B 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	73.4% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 100/236	easy · avg 70%	▇ 2.4%	sharp · at its level · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	92.6% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 101/246	very easy · avg 92%	▇ 2.2%	sharp · maxed out · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	65.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 83/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	30.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 105/243	medium · avg 37%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 148/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.7% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #100 of 258 · 6.2% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Quyet-1.0-Large here, though they rank higher overall. Trails Jev-Style 2B v4, Sieve 2B v3, StartLux-Decision v1.1 0.8B 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	45.6% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 162/246	medium · avg 38%	▇ 2.2%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 156/246	medium · avg 47%	▇ 2.1%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	60.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 53/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	69.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 127/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	89.4% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 117/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	71.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 44/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	29.9% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #92 of 256 · 23% of its score · 9 tests

Beats Turion Jev 31B, AJev lm6q (Gemma 4 31B), FlexDM · Gemma-4-31B (decision readout) here, though they rank higher overall. Trails Decider 4B 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	93.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 168/246	very easy · avg 85%	▇▇ 5.9%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	78.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 134/246	easy · avg 74%	▇▇ 5.4%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	61.4% ✎	▁▂▃▅▅█▂····▁ beats 108/246	medium · avg 60%	▇▇ 5.2%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	40.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 93/246	medium · avg 44%	▇ 2.2%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	82.9% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 195/246	easy · avg 71%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ACOS (per-review F1) submitted	12.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 68/246	hard · avg 22%	▇ 1.0%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	59.4% ✎	▁▁▁▂▅▄▄▃▄▆█▄ beats 106/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	78.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 161/246	easy · avg 66%	▇ 0.8%	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	84.4% ✎	▁···▁▁▁▁▃▆█▃ beats 95/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #165 of 247 · 9.1% of its score · 6 tests

Beats PurpleMIST-Flash-1.0 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	59.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 96/246	medium · avg 61%	▇▇ 3.9%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 102/246	medium · avg 60%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	77.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 82/246	easy · avg 83%	▇ 1.3%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	64.0% ✎	▁········▁▇█ beats 160/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	8.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 92/237	hard · avg 21%	▇ 0.7%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	44.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 131/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #138 of 263 · 45% of its score · 14 tests

Beats Winnow-12B (DecisionBench b6ac22b0), Amber Hybrid 4B (decision readout), StartLux-Decision v1.1 2B here, though they rank higher overall. Trails mmastrac diffgemma (decision readout), djev diffgemma (decision readout), Kev 9B v2 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	54.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 130/246	medium · avg 46%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	75.0% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 120/246	easy · avg 70%	▇▇▇ 7.2%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	67.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 116/246	easy · avg 66%	▇▇▇ 6.4%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	93.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 114/246	very easy · avg 90%	▇▇ 4.7%	sharp
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	44.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 127/246	medium · avg 45%	▇ 3.3%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	71.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 96/246	easy · avg 78%	▇ 3.2%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	40.8% ✎	▂▆▅▅▆█▆▃▁··▁ beats 114/246	medium · avg 39%	▇ 2.9%	blunt · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	97.5% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 108/246	very easy · avg 96%	▇ 2.5%	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	31.8% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 168/246	hard · avg 22%	▇ 1.2%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	55.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 79/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	48.4% ✎	██▄▃▃▄▁▁···▁ beats 103/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	66.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 102/246	easy · avg 71%	▇ 1.0%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	13.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 94/246	hard · avg 16%	▇ 0.6%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	12.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 108/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 7.8% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	46.7000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 128/247	avg 41.206 points	▇▇ 5.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	40.1900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 128/247	avg 38.861 points	▇ 2.8%	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/eljiwo ↗

$ how the score was worked out · Decision Index 0.4.1 99%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 52.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.7%	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]	29.9%	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