whatmodel.sh / decision / Jobe Qwen3.5-4B (decision readout)

Jobe Qwen3.5-4B (decision readout)

+ contribute

Jobe Qwen3.5-4B (decision readout) is a source-available decision implementation from MantisShrimpdev. Its published size is 4.66B parameters.

Catalogue identity notes

Exact Decision Index tested engine jobe; reported model Jobe Qwen3.5-4B. Type: inference technique; technique: autoregressive. Published checkpoint/base reference: Qwen/Qwen3.5-4B. Implementation: https://github.com/MantisShrimpdev/jobe. Comparison entry; no current run command, API price or speed inferred from the benchmark.

Model information sources

· Parameter count ↗

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

45.0±1.1#243 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Jobe Qwen3.5-4B (decision readout), out of 357 with a score.

#	model	score	where	RAM	released
243	RSI-Jev v3.0 2B (JevBench mini) Shanghua Gao	45±2	source code
244	Metask-Jev-4B Metask-AI-Lab	45±1	model files
245	Jobe Qwen3.5-4B (decision readout) MantisShrimpdev	45±1	source code
246	OneJev1.6-0.8B OmniJev	45±1	model files		2026-10-17
247	GLiClass v4 edge (0.4B) Knowledgator Engineering	45±1	local	~2.7GB

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #143 of 250 · 8.6% 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, 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: BFCL (case exact accuracy) submitted	93.0% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 108/246	very easy · avg 92%	▇ 3.3%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	46.1% ✎	▁▁▁▁▁▁▁▃▃▂█▂ beats 41/236	easy · avg 70%	▇ 2.5%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	54.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 56/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	59.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 60/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	8.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 66/243	medium · avg 37%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.5% ✎	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▁▁▁·▁▁▁▃▃▃█▅ #210 of 258 · 5.6% of its score · 7 tests

Beats Metask-Jev-4B here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Mola-68M 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	41.2% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 109/246	medium · avg 38%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	35.8% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 48/246	medium · avg 47%	▇ 1.8%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	61.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 61/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	60.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 86/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	54.4% ✎	▁▁▁▁▁▁▁▃▃▆█▄ beats 29/238	easy · avg 83%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	62.4% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 26/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	56.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #153 of 256 · 24% of its score · 9 tests

Beats PurpleMIST-Flash-1.0, Hopper 12B (trained), Jev-Omni here, though they rank higher overall. Trails Decider 2B, Crivo-1B 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	83.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 102/246	very easy · avg 85%	▇▇▇ 7.7%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	71.9% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 84/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	54.5% ✎	▁▂▃▅▅█▂····▁ beats 80/246	medium · avg 60%	▇▇ 4.8%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	39.0% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 87/246	medium · avg 44%	▇ 1.8%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	59.2% ✎	▁▁▁▁▁▁▁▃▂▇▇█ beats 47/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	43.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 50/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	65.8% ✎	▁···▁▁▁▁▃▆█▃ beats 32/246	easy · avg 84%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	57.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 67/246	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: ACOS (per-review F1) submitted	13.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 74/246	hard · avg 22%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #138 of 247 · 8.3% 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-68M, Crivo-150M v2, vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B) 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	58.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 88/246	medium · avg 61%	▇ 3.6%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.5% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 104/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	85.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 108/246	easy · avg 83%	▇ 1.5%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	56.9% ✎	▁········▁▇█ beats 67/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	5.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 75/237	hard · avg 21%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	44.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 123/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #163 of 263 · 46% 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.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	43.6% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 92/246	medium · avg 46%	▇▇▇ 8.2%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	71.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 99/246	easy · avg 70%	▇▇▇ 7.4%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	91.7% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 103/246	very easy · avg 90%	▇▇▇ 7.0%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	57.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 77/246	easy · avg 66%	▇▇ 6.2%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	96.8% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 102/246	very easy · avg 96%	▇▇ 4.6%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	66.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 61/246	easy · avg 78%	▇ 3.4%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	24.2% ✎	▁··▄█▆▆▆▅▅▃▁ beats 53/246	medium · avg 45%	▇ 2.7%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	37.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 98/246	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	54.4% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 59/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	39.1% ✎	██▄▃▃▄▁▁···▁ beats 49/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	56.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 50/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	20.2% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 74/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	13.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 95/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 82/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.8% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	33.6800 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 72/247	avg 41.206 points	▇▇ 4.4%	blunt
Decision Index 0.4.1: private new domains (equated points)	25.3600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 84/247	avg 38.861 points	▇ 2.4%	blunt

$ where to run it

Implementation and setup instructions ↗
Published implementation and setup documentation verified. This entry describes a decision readout or evaluated configuration, not necessarily separate trained weights. Follow the referenced version and model settings; hardware compatibility has not been verified. Source · checked 2026-10-31.

Model repository and documentation: github.com/MantisShrimpdev ↗

$ 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		= 45.0

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.5%	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]	56.6%	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