whatmodel.sh / decision / deck31b (Gemma 4 31B) (decision readout)

deck31b (Gemma 4 31B) (decision readout)

+ contribute

deck31b (Gemma 4 31B) (decision readout) is a source-available decision implementation from krishna-gogineni-765. Its published size is 32.68B parameters.

Catalogue identity notes

Exact Decision Index tested engine deck31b; reported model deck31b (Gemma 4 31B). Type: inference technique; technique: autoregressive. Implementation: https://github.com/krishna-gogineni-765/deck31b. 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.

62.5±1.3#82 of 355 decision modelsfrom 44 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of deck31b (Gemma 4 31B) (decision readout), out of 357 with a score.

#	model	score	where	released
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
84	SynACK Decide 26B-A4B v7 SkyPanther	62±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #11 of 250 · 6.2% of its score · 6 tests

Beats Jeffan-31b-1710, Sieve 31B v3, Fastino GLiDE 1.2 here, though they rank higher overall. Trails 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)	84.8% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 151/236	easy · avg 70%	▇ 1.9%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy)	98.1% ✎	▁▂▁▁▁▂▂▄▅▆█▃ beats 236/246	very easy · avg 92%	▇ 1.2%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy)	64.8% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 157/243	medium · avg 37%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10)	61.2% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 78/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy)	77.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 126/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective))	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▁▁▁·▁▁▁▁▃▃█▅ #120 of 258 · 7.0% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Quyet-1.0-Large 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)	42.7% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 124/246	medium · avg 38%	▇ 2.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1)	53.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 131/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy)	75.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 126/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy)	89.0% ✎	█▅▅▄▃▃▁▁▁▁·▁ beats 208/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1)	89.9% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 126/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1)	78.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 74/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1)	3.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #110 of 256 · 21% 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)	73.7% ✎	▁▂▃▅▅█▂····▁ beats 187/246	medium · avg 60%	▇▇ 5.3%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1)	83.5% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 195/246	easy · avg 74%	▇▇ 5.1%	typical
Decision Index 0.4.1: HellaSwag (accuracy)	92.1% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 143/246	very easy · avg 85%	▇ 3.5%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English)	51.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 141/246	medium · avg 44%	▇ 2.6%	at its level
Decision Index 0.4.1: ACOS (per-review F1)	20.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 110/246	hard · avg 22%	▇ 1.5%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1)	69.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 132/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1)	72.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 89/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class)	79.3% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 166/246	easy · avg 66%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1)	93.4% ✎	▁···▁▁▁▁▃▆█▃ beats 204/246	easy · avg 84%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #116 of 247 · 10% 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)	74.8% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 187/246	medium · avg 61%	▇▇ 3.9%	at its level
Decision Index 0.4.1: Humicroedit (accuracy)	62.9% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 165/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy)	25.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 138/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy)	65.6% ✎	▁········▁▇█ beats 194/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy)	89.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 131/246	easy · avg 83%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy)	48.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 175/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #56 of 263 · 42% 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)	69.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 203/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy)	86.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 203/246	easy · avg 70%	▇▇ 6.1%	sharp
Decision Index 0.4.1: BBH (accuracy)	76.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 169/246	easy · avg 66%	▇▇ 5.9%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy)	51.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 203/246	medium · avg 39%	▇ 3.6%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice))	72.8% ✎	▁··▄█▆▆▆▅▅▃▁ beats 197/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy)	84.9% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 159/246	easy · avg 78%	▇ 2.8%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy)	97.2% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 205/246	very easy · avg 90%	▇ 2.3%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy)	30.9% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 157/246	hard · avg 22%	▇ 1.8%	at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy)	64.1% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 167/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy)	80.7% ✎	██▄▃▃▄▁▁···▁ beats 201/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ARC-Easy (accuracy)	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 186/246	very easy · avg 96%	▇ 1.0%	sharp · maxed out · noisy
Decision Index 0.4.1: CLadder (accuracy)	76.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 159/246	easy · avg 71%	▇ 0.9%	typical
Decision Index 0.4.1: ChessBench (accuracy)	21.9% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 185/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy)	13.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 154/246	very hard · avg 13%	▇ 0.0%	blunt

other tests4 not in a task · 13% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	58.2300 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 196/247	avg 41.206 points	▇▇ 6.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	70.2900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 214/247	avg 38.861 points	▇ 3.3%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	73.0251 points ✎	▃···▃·▃▃█▅▅█ beats 12/13	avg 32.166 points	▇ 2.7%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	82.1564 points ✎	▂······▂▆▂██ beats 4/13	avg 70.133 points	▇ 0.7%	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/krishna-gogineni-765 ↗

$ how the score was worked out · Decision Index 0.4.1 96%, Benchmark Heaven (own decisio… 3%

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	42	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%	CC BY 4.0
Benchmark Heaven (own decision evaluations)	2	▇ 3%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 62.5

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]	3.8%	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