JEV-27B

+ contribute

JEV-27B is an open-weights decision model from AutoTrust AI Lab. Its published size is 27.8B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine jev-27b; reported model JEV-27B. Type: full fine-tune; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

· Weights licence ↗ · Parameter count ↗

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

59.6±1.3#112 of 355 decision modelsfrom 43 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of JEV-27B, out of 357 with a score, then more from AutoTrust AI Lab.

#	model	score	where	released
111	Cerno 9B v1.1 apertixai	60±1	model files	2026-10-19
112	openjev-sglang (DecisionBench 1355db6a) ekzhang	60±2	model files
113	JEV-27B AutoTrust AI Lab	60±1	model files
114	simple-jev · Qwen3.8-27B (featherless) (decision readout) featherless-ai	60±1	source code
115	OneJev1.6-4B OmniJev	60±1	model files	2026-10-17
	more from AutoTrust AI Lab
18	AutoTrust-JEV-27B v1.1 AutoTrust AI Lab	70±1	model files	2026-10-17
69	JEV-27B-VL AutoTrust AI Lab	64±4	model files
83	JEV-35B AutoTrust AI Lab	63±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #99 of 250 · 6.8% 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	82.9% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 133/236	easy · avg 70%	▇ 2.1%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.0% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 147/246	very easy · avg 92%	▇ 1.4%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	52.3% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 135/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	78.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 132/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 155/246	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▁▁▁·▁▁▁▁▃▃█▅ #107 of 258 · 7.9% of its score · 8 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Quyet-1.0-Large here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-0.8b, Jev-Style 2B v4 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	48.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 206/246	medium · avg 38%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	54.6% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 145/246	medium · avg 47%	▇ 2.4%	at its level
GEO Citation · listwise Spearman (October 2026)	0.5783 spearman-rho ✎	▃···▃······█ beats 4/4	avg 0.256 spearman-rho	▇ 0.9%	blunt
Decision Index 0.4.1: HoVer (accuracy) submitted	73.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 116/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	61.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 94/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	84.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 76/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	74.2% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 56/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	61.2% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #107 of 256 · 22% of its score · 9 tests

Beats jev-brain · Gemma-4-31B (decision readout), decisio 0.6.0 (Gemma 4 31B) (decision readout), deck31b (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	77.2% ✎	▁▂▃▅▅█▂····▁ beats 217/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	84.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 205/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	92.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 149/246	very easy · avg 85%	▇▇ 4.2%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	42.0% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 97/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	19.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 106/246	hard · avg 22%	▇ 1.4%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	54.8% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 93/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	75.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 118/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.9% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 188/246	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	83.4% ✎	▁···▁▁▁▁▃▆█▃ beats 90/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #76 of 247 · 10% of its score · 6 tests

Beats Jev 1.13, Quyet-1.0-Large, jev-brain · Gemma-4-31B (decision readout) 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	68.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 141/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.2% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 122/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.0% ✎	▁········▁▇█ beats 144/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	40.3% ✎	▄▅▅▃▆▅▃▅▃▅▃█ beats 162/237	hard · avg 21%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	92.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 172/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 73/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #88 of 263 · 44% of its score · 14 tests

Beats StartLux-Decision v1.1 4B, KnowLine 4B Gen5.5, Jeffan-4B-2010 here, though they rank higher overall. Trails Solar Decide, Clef-flash, Xor 1.2 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	61.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 165/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	83.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 171/246	easy · avg 70%	▇▇▇ 6.6%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	78.9% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 185/246	easy · avg 66%	▇▇ 6.2%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	61.6% ✎	▁··▄█▆▆▆▅▅▃▁ beats 165/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	44.9% ✎	▂▆▅▅▆█▆▃▁··▁ beats 153/246	medium · avg 39%	▇ 3.5%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	82.6% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 137/246	easy · avg 78%	▇ 3.0%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.7% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 180/246	very easy · avg 90%	▇ 2.9%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	33.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 191/246	hard · avg 22%	▇ 1.6%	at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 184/246	very easy · avg 96%	▇ 1.3%	sharp · maxed out · noisy
Decision Index 0.4.1: MuSR (accuracy) submitted	62.4% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 153/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	73.7% ✎	██▄▃▃▄▁▁···▁ beats 179/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	70.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 129/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	16.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 126/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	7.0% ✎	▃▁▂▃▆█▇▅▅▃▁▁ beats 2/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 9.0% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	53.7900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 162/247	avg 41.206 points	▇▇ 5.8%	blunt
Decision Index 0.4.1: private new domains (equated points)	62.6700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 194/247	avg 38.861 points	▇ 3.2%	blunt

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/autotrust ↗

$ how the score was worked out · Decision Index 0.4.1 98%, Citead GEO Citation Benchmark… 1%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%	CC BY 4.0
Citead GEO Citation Benchmark (October 2026)	1	▇ 1%	CC BY-SA 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 59.6

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]	61.2%	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