whatmodel.sh / decision / djev diffgemma (decision readout)

djev diffgemma (decision readout)

+ contribute

djev diffgemma (decision readout) is a source-available decision implementation from Davipar. Its published size is 25.82B parameters.

Catalogue identity notes

Exact Decision Index tested engine djev; reported model djev diffgemma. Type: inference technique; technique: diffusion. Published checkpoint/base reference: google/diffusiongemma-26B-A4B-it. Implementation: https://github.com/Davipar/djev-dev. 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.

49.8±1.1#208 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of djev diffgemma (decision readout), out of 357 with a score, then more from Davipar.

#	model	score	where	released
208	Sieve 9B Sthānika AI	50±1	model files	2026-10-13
209	Kev 9B v2 Jared Palmer	50±1	model files	2026-09-30
210	djev diffgemma (decision readout) Davipar	50±1	source code
211	JevK5 v0.3 (JevBench mini) Alibi Serikbay	50±2	source code
212	FlyMy.AI Decision 4B v1.6 FlyMy.AI	50±1	model files
	more from Davipar
151	djev-dev (DecisionBench f7f5b7f5) Davipar	56±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #142 of 250 · 7.3% 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	92.9% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 107/246	very easy · avg 92%	▇ 2.3%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	70.7% ✎	▁▁▁▁▁▁▁▂▃▃█▂ beats 91/236	easy · avg 70%	▇ 2.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	54.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 52/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 48/243	medium · avg 37%	▇ 0.9%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	54.2% ✎	▁▁▁▁▁·▁▁▃▄█▁ beats 40/246	medium · avg 60%	▇ 0.8%	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▁▁▁·▁▁▁▁▃▃█▅ #96 of 258 · 5.4% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Quyet-1.0-Large here, though they rank higher overall. Trails Jev-Style 2B v4, Sieve 2B v3, StartLux-Decision v1.1 0.8B 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	30.8% ✎	▁▁▁▁▁▁▁▃▂▄▇█ beats 52/246	medium · avg 38%	▇ 1.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	56.4% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 173/246	medium · avg 47%	▇ 1.8%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	66.8% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 87/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	86.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 195/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	13.5% ✎	▁▁▁▁▃▁▁▂▃▆█▄ beats 13/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	69.4% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 39/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	14.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #148 of 256 · 21% of its score · 9 tests

Beats Solar Decide, JoshuaSP diffgemma (decision readout), PurpleMIST-Flash-1.0 here, though they rank higher overall. Trails Decider 2B, Crivo-1B, LatentMesh Blitz 2B v1 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	83.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 104/246	very easy · avg 85%	▇▇ 5.9%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	75.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 99/246	easy · avg 74%	▇▇ 4.9%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	59.8% ✎	▁▂▃▅▅█▂····▁ beats 105/246	medium · avg 60%	▇▇ 4.6%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	59.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 183/246	medium · avg 44%	▇ 1.8%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	70.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 73/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	64.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 118/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	27.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 156/246	hard · avg 22%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	73.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 116/246	easy · avg 66%	▇ 0.7%	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	84.4% ✎	▁···▁▁▁▁▃▆█▃ beats 94/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #108 of 247 · 7.9% 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	60.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 104/246	medium · avg 61%	▇ 3.5%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.9% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 116/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	90.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 143/246	easy · avg 83%	▇ 1.2%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	59.4% ✎	▁········▁▇█ beats 96/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	15.0% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 121/237	hard · avg 21%	▇ 0.6%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	46.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 157/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #127 of 263 · 41% of its score · 14 tests

Beats Winnow-12B (DecisionBench b6ac22b0), Cerno 4B v1.1, Amber Hybrid 4B (decision readout) 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	44.0% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 95/246	medium · avg 46%	▇▇▇ 8.4%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	79.4% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 151/246	easy · avg 70%	▇▇▇ 6.6%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	67.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 117/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	95.2% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 144/246	very easy · avg 90%	▇▇ 4.9%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	69.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 79/246	easy · avg 78%	▇ 3.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.4% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 148/246	very easy · avg 96%	▇ 2.8%	sharp · maxed out · noisy
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	19.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 33/246	medium · avg 45%	▇ 2.8%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	47.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 171/246	medium · avg 39%	▇ 2.5%	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	63.3% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 162/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	28.2% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 126/246	hard · avg 22%	▇ 1.0%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	46.8% ✎	██▄▃▃▄▁▁···▁ beats 95/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	63.9% ✎	▁███▆▅▃▃▁▁▁▁ beats 89/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	14.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 105/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 100/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #66 of 79 · 10% of its score · 12 tests

Trails LiquidAI d1-omni-600M, Valen-2B, TokenRhythm NeoHorse-Jev-4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	64.5100 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 19/61	avg 63.423 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	32.5100 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 34/61	avg 22.797 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	54.5000 points ✎	▁·▁▁▁▃·▂▁▃▅█ beats 9/61	avg 66.987 points	▇ 1.1%	blunt
Decision Index Vision 0.4: private same skills (points)	40.3500 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 10/61	avg 48.067 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	41.3000 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 40/61	avg 28.443 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	50.0600 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 10/61	avg 53.651 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	39.6000 points ✎	▂▃▁▁▁▃▁▅▅▆██ beats 3/61	avg 62.137 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	73.7700 points ✎	▁·▁▃▁▁▃▁▂▂▅█ beats 6/61	avg 83.859 points	▇ 0.7%	blunt

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	24.9200 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 34/61	avg 19.676 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	41.5200 points ✎	▁···▁▂▃▂█▄▂▃ beats 12/61	avg 44.994 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	62.6000 points ✎	▁▁▁▁▃▁▁▁▄█▃▃ beats 8/61	avg 67.662 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	89.7800 points ✎	▁··▁▁▁▁▁▂▄█▁ beats 21/61	avg 85.184 points	▇ 0.4%	blunt

other tests2 not in a task · 6.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	41.0600 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 102/247	avg 41.206 points	▇▇ 4.3%	blunt
Decision Index 0.4.1: private new domains (equated points)	33.7900 points ✎	▃█▃▃▃▆▃▃▄▄▄▄ beats 100/247	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/Davipar ↗

$ how the score was worked out · Decision Index 0.4.1 90%, Decision Index Vision 0.4 10%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇ 10%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 49.8

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]	14.8%	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