whatmodel.sh / decision / FlexDM · Gemma-4-31B (decision readout)

FlexDM · Gemma-4-31B (decision readout)

+ contribute

FlexDM · Gemma-4-31B (decision readout) is a source-available decision implementation from 1000luca. Its published size is 31.27B parameters.

Catalogue identity notes

Exact Decision Index tested engine flexdm-gemma-4-31b; reported model FlexDM · Gemma-4-31B. Type: inference technique; technique: autoregressive. Implementation: https://github.com/1000luca/FlexDM/tree/v1.0. 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.

66.2±1.4#46 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

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

#	model	score	where
44	Lychee-27B LycheeAI	66±1	model files
45	Darwin-27B-ZTC FINAL_Bench	66±1	model files
46	FlexDM · Gemma-4-31B (decision readout) 1000luca	66±1	source code
47	Standard One 35B SH (v1) Standard Thinking	66±1	model files
48	allec-oavg (Gemma 4 31B) plantwaterer	66±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #33 of 250 · 5.9% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, Ainvest-Decision-27B v1.0 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	85.2% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 167/236	easy · avg 70%	▇ 1.7%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	66.3% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 168/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	70.5% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 169/243	medium · avg 37%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 215/246	very easy · avg 92%	▇ 1.0%	sharp · maxed out · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	85.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 174/246	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▁▁▁·▁▁▁▁▃▃█▅ #50 of 258 · 7.7% of its score · 7 tests

Beats H2O Lightning 31B v1.1, AutoTrust-JEV-27B v1.1, d1.1 (hosted) here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B 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	48.6% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 209/246	medium · avg 38%	▇ 3.2%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	58.8% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 202/246	medium · avg 47%	▇ 2.8%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	81.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 157/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	96.0% ✎	█▅▅▄▃▂▁▃▁▁·▁ beats 232/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	80.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 96/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	91.5% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 147/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	8.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #101 of 256 · 22% of its score · 9 tests

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	79.9% ✎	▁▂▃▅▅█▃····▁ beats 234/246	medium · avg 60%	▇▇ 5.5%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	79.7% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 152/246	easy · avg 74%	▇▇ 5.2%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	92.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 150/246	very easy · avg 85%	▇ 3.0%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	59.8% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 184/246	medium · avg 44%	▇ 2.8%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	40.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 202/246	hard · avg 22%	▇ 1.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	80.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 225/246	medium · avg 62%	▇ 1.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	78.8% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 153/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	78.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 159/246	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) submitted	93.1% ✎	▁···▁▁▁▁▃▆█▃ beats 190/246	easy · avg 84%	▇ 0.5%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #69 of 247 · 10% of its score · 6 tests

Beats mogan-decision-31B-it here, though they rank higher overall. Trails Amber 0.4B, Crivo-1B, Kas 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	79.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 213/246	medium · avg 61%	▇▇ 4.0%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	64.5% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 197/246	medium · avg 60%	▇ 2.3%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	38.3% ✎	▄▅▅▃▆▅▃▅▃▅▃█ beats 158/237	hard · avg 21%	▇ 1.3%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.3% ✎	▁········▁▇█ beats 185/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	93.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 178/246	easy · avg 83%	▇ 0.9%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	50.2% ✎	▁▂▄█▇▅▃▁▄▄▁▁ beats 178/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #34 of 263 · 43% of its score · 14 tests

Beats vera-large, KnowLine 26B-A4B Gen2.5, OneJev1.6-27B here, though they rank higher overall. Trails Solar Decide, Clef-omni, Clef 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	72.0% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 220/246	medium · avg 46%	▇▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	78.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 183/246	easy · avg 66%	▇▇ 5.9%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	88.0% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 223/246	easy · avg 70%	▇▇ 5.9%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	49.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 188/246	medium · avg 39%	▇▇ 4.1%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	72.6% ✎	▁··▄█▆▆▆▅▅▃▁ beats 195/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	89.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 197/246	easy · avg 78%	▇ 2.7%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	34.1% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 193/246	hard · avg 22%	▇ 2.1%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.6% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 228/246	very easy · avg 90%	▇ 1.9%	sharp · maxed out

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	68.8% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 207/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	86.3% ✎	██▄▃▃▄▁▁···▁ beats 222/246	medium · avg 58%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	23.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 211/246	hard · avg 16%	▇ 1.0%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	83.9% ✎	▁███▆▅▃▃▁▁▁▁ beats 198/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 213/246	very easy · avg 96%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	16.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 223/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 11% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	62.6600 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 230/247	avg 41.206 points	▇▇▇ 6.8%	blunt
Decision Index 0.4.1: private new domains (equated points)	74.9200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 238/247	avg 38.861 points	▇▇ 3.8%	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/1000luca ↗

$ 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		= 66.2

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]	8.0%	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