whatmodel.sh / decision / decisio 0.6.0 (Gemma 4 31B) (decision readout)

decisio 0.6.0 (Gemma 4 31B) (decision readout)

+ contribute

decisio 0.6.0 (Gemma 4 31B) (decision readout) is a source-available decision implementation from aminry, released 5 October 2026. Its published size is 31.27B parameters.

Catalogue identity notes

Exact Decision Index tested engine decisio-0.6.0-gemma-4-31b; reported model decisio 0.6.0 (Gemma 4 31B). 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.

62.6±1.4#81 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of decisio 0.6.0 (Gemma 4 31B) (decision readout), out of 357 with a score, then more from aminry.

#	model	score	where	released
79	Sieve-Vision-27B Sthānika AI	63±4	model files
80	reflex-27b (DecisionBench 1d4bf0f2) kshetrajna12	63±2	model files
81	decisio 0.6.0 (Gemma 4 31B) (decision readout) aminry	63±1	source code	2026-10-05
82	deck31b (Gemma 4 31B) (decision readout) krishna-gogineni-765	63±1	source code
83	JEV-35B AutoTrust AI Lab	63±1	model files
	more from aminry
149	decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout) aminry	56±1	source code	2026-10-04
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▁▃▁▁▁▂▃▄▆██▆ #24 of 250 · 6.4% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, KnowLine 31B Gen1 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni 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	85.4% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 177/236	easy · avg 70%	▇ 1.9%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.9% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 230/246	very easy · avg 92%	▇ 1.2%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	61.4% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 148/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	61.3% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 80/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	77.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 125/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	80.0% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #113 of 258 · 7.3% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Quyet-1.0-Large, OneJev1.6-9B here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-0.8b, Kas 4B 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	43.9% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 137/246	medium · avg 38%	▇ 2.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	54.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 142/246	medium · avg 47%	▇ 2.6%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	75.6% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 125/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	87.5% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 201/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	90.1% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 129/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	78.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 78/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	1.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #108 of 256 · 22% of its score · 9 tests

Beats jev-brain · Gemma-4-31B (decision readout) here, though they rank higher overall. Trails Decider 4B, jiwo 4B v2, Sieve 4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	73.7% ✎	▁▂▃▅▅█▂····▁ beats 188/246	medium · avg 60%	▇▇ 5.5%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	83.5% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 194/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	92.3% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 144/246	very easy · avg 85%	▇ 3.6%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	50.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 135/246	medium · avg 44%	▇ 2.7%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	21.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 120/246	hard · avg 22%	▇ 1.6%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	68.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 130/246	medium · avg 62%	▇ 1.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	72.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 92/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	78.3% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 162/246	easy · avg 66%	▇ 0.8%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	93.1% ✎	▁···▁▁▁▁▃▆█▃ beats 191/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #117 of 247 · 10% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B) 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	73.9% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 178/246	medium · avg 61%	▇▇ 4.1%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.5% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 162/246	medium · avg 60%	▇ 2.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	26.2% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 142/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.1% ✎	▁········▁▇█ beats 182/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	89.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 130/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	48.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 171/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #54 of 263 · 44% of its score · 14 tests

Beats OneJev1.6-27B, baselabs elephant-1 (9B), StartLux-Decision v1.1 9B here, though they rank higher overall. Trails Solar Decide, Clef-flash, Clef-omni 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	69.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 205/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	86.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 205/246	easy · avg 70%	▇▇▇ 6.3%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	76.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 167/246	easy · avg 66%	▇▇ 6.1%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	52.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 213/246	medium · avg 39%	▇▇ 3.8%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	71.8% ✎	▁··▄█▆▆▆▅▅▃▁ beats 193/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	85.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 162/246	easy · avg 78%	▇ 2.9%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.2% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 208/246	very easy · avg 90%	▇ 2.4%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	32.3% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 174/246	hard · avg 22%	▇ 1.9%	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	64.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 166/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	83.2% ✎	██▄▃▃▄▁▁···▁ beats 208/246	medium · avg 58%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 198/246	very easy · avg 96%	▇ 1.0%	sharp · maxed out · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	76.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 162/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	22.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 188/246	hard · avg 16%	▇ 0.9%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 200/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 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)	58.1200 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 194/247	avg 41.206 points	▇▇▇ 6.3%	blunt
Decision Index 0.4.1: private new domains (equated points)	69.5200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 211/247	avg 38.861 points	▇ 3.5%	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		= 62.6

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	80.0%	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]	1.0%	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