whatmodel.sh / decision / decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout)

decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout)

+ contribute

decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout) is a source-available decision implementation from aminry, released 4 October 2026. Its published size is 35.95B parameters.

Catalogue identity notes

Exact Decision Index tested engine decisio-0.4.0-qwen3.6-35b-a3b; reported model decisio 0.4.0 (Qwen3.6-35B-A3B). Type: inference technique; technique: autoregressive. Implementation: https://github.com/aminry/decisio. Comparison entry; no current run command, API price or speed inferred from the benchmark.

Model information sources

Release date ↗ · Parameter count ↗

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

55.7±1.3#147 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), out of 357 with a score, then more from aminry.

#	model	score	where	released
147	Sieve-Vision-4B Sthānika AI	56±4	model files
148	xor-26b-a4b-v1.1 Juspay Technologies	56±4	model files	2026-10-09
149	decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout) aminry	56±1	source code	2026-10-04
150	Jegue 0.1 (9B) fdemelo	56±1	model files
151	djev-dev (DecisionBench f7f5b7f5) Davipar	56±2	model files
	more from aminry
81	decisio 0.6.0 (Gemma 4 31B) (decision readout) aminry	63±1	source code	2026-10-05
166	decisio 0.4.0 (Gemma 4 12B) (decision readout) aminry	54±1	source code	2026-10-04

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #101 of 250 · 7.4% of its score · 6 tests

Beats Jev 1.13, Xor 26B-A4B v1.2, Senova-4B v2 here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, 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: API-Bank (accuracy) submitted	81.7% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 124/236	easy · avg 70%	▇ 2.3%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.0% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 149/246	very easy · avg 92%	▇ 1.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	39.8% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 114/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	71.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 99/246	easy · avg 72%	▇ 1.1%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	62.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 93/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.9% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #171 of 258 · 6.6% of its score · 7 tests

Beats Solar Decide here, though they rank higher overall. Trails Bosun v3.1 1.7B LoRA, Dinah-1, DecisionTune 1.0 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	44.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 144/246	medium · avg 38%	▇ 2.4%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	45.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 82/246	medium · avg 47%	▇ 2.3%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	70.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 99/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	75.3% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 154/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	82.2% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 73/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	74.6% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 58/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	46.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #86 of 256 · 23% of its score · 9 tests

Beats Turion Jev 31B, AJev lm6q (Gemma 4 31B), oenogarum (Gemma 4 31B) here, though they rank higher overall. Trails Sieve 4B, Amber 4B, Decider 35B-A3B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	77.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 116/246	easy · avg 74%	▇▇ 5.4%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	68.6% ✎	▁▂▃▅▅█▂····▁ beats 147/246	medium · avg 60%	▇▇ 5.3%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	94.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 173/246	very easy · avg 85%	▇▇ 5.1%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	47.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 122/246	medium · avg 44%	▇ 2.3%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	17.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 92/246	hard · avg 22%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	73.3% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 97/246	easy · avg 71%	▇ 1.1%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	49.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 72/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	70.2% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 96/246	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	80.3% ✎	▁···▁▁▁▁▃▆█▃ beats 69/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #106 of 247 · 9.4% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B), decisio 0.6.0 (Gemma 4 31B) (decision readout) 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	68.8% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 142/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.8% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 111/246	medium · avg 60%	▇ 1.9%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	90.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 144/246	easy · avg 83%	▇ 1.2%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	61.5% ✎	▁········▁▇█ beats 118/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	14.5% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 118/237	hard · avg 21%	▇ 0.9%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	44.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 129/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #95 of 263 · 45% of its score · 14 tests

Beats StartLux-Decision v1.1 4B, KnowLine 4B Gen5.5, Jeffan-4B-2010 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	61.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 163/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	83.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 175/246	easy · avg 70%	▇▇▇ 7.0%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	69.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 131/246	easy · avg 66%	▇▇▇ 6.4%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.1% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 164/246	very easy · avg 90%	▇▇ 3.8%	sharp · maxed out
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	35.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 94/246	medium · avg 45%	▇ 3.5%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	51.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 204/246	medium · avg 39%	▇ 3.2%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	80.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 130/246	easy · avg 78%	▇ 3.1%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.1% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 202/246	very easy · avg 96%	▇ 1.9%	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	23.2% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 91/246	hard · avg 22%	▇ 1.4%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	58.1% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 108/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	62.5% ✎	██▄▃▃▄▁▁···▁ beats 148/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	62.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 73/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	16.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 123/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 73/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 8.4% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	48.6700 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 138/247	avg 41.206 points	▇▇ 5.4%	blunt
Decision Index 0.4.1: private new domains (equated points)	54.0600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 167/247	avg 38.861 points	▇ 3.0%	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/aminry ↗

$ 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		= 55.7

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.9%	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]	46.6%	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