whatmodel.sh / decision / GLiClass v4 edge (0.4B)

GLiClass v4 edge (0.4B)

+ contribute

GLiClass v4 edge (0.4B) is an open-weights decision model from Knowledgator Engineering. Its published size is 0.44B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine gliclass-v4-edge; reported model GLiClass v4 edge (0.4B). Type: full fine-tune; technique: encoder. No 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. Reviewed Ollaya local route added 2026-10-31: gliclass:v4-edge, manifest 3b1849b2b5ec38109cbf8772715bccaf8f546ab48f6ecefdee41f4d6af1c5b39, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (2677 MiB, rounded upward to 2.7 GiB) on RTX 5090 during the short five-question triage workload, not download size or a maximum-context guarantee. Runtime installation is required; no fresh execution performed here. Historical benchmark adapter and input protocol still vary by result.

Model information sources

· Weights licence ↗ · Parameter count ↗

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

44.6±1.0#245 of 355 decision modelsfrom 56 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of GLiClass v4 edge (0.4B), out of 357 with a score.

#	model	score	where	RAM	released
245	Jobe Qwen3.5-4B (decision readout) MantisShrimpdev	45±1	source code
246	OneJev1.6-0.8B OmniJev	45±1	model files		2026-10-17
247	GLiClass v4 edge (0.4B) Knowledgator Engineering	45±1	local	~2.7GB
248	Jevstral 8B AmirBraham	44±1	model files
249	crystal-0.8b Kyunghwan-kim	44±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #173 of 250 · 7.2% of its score · 6 tests

Beats LiquidAI d1-3B, Decider 4B, Together Tev1 Qwen3.5-4B here, though they rank higher overall. Trails JevK5 Lite, Mola-150M, Gevva E2B 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	90.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 76/246	very easy · avg 92%	▇ 2.9%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	82.9% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 132/236	easy · avg 70%	▇ 2.1%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	62.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 73/246	easy · avg 72%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	55.0% ✎	▁▁▁▁▁·▁▁▃▄█▁ beats 43/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	12.5% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 73/243	medium · avg 37%	▇ 0.6%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	68.2% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #141 of 258 · 4.6% of its score · 7 tests

Beats Quyet-1.0-Large, Decider chat · Qwen3.6-27B (decision readout), Sieve 9B v2 here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-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	31.4% ✎	▁▁▁▁▁▁▁▃▂▄▇█ beats 55/246	medium · avg 38%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	51.6% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 114/246	medium · avg 47%	▇ 1.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	83.8% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 176/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	93.4% ✎	█▅▅▄▃▂▃▁▁▁·▁ beats 225/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	92.3% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 161/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.8% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 193/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	60.1% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #156 of 256 · 20% of its score · 9 tests

Beats PurpleMIST-Flash-1.0, Hopper 12B (trained), Jev-Omni here, though they rank higher overall. Trails DecisionTune 1.0, Decider 2B, Crivo-1B 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	82.8% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 99/246	very easy · avg 85%	▇▇▇ 6.6%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	71.9% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 85/246	easy · avg 74%	▇▇ 4.5%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	61.7% ✎	▁▂▃▅▅█▂····▁ beats 110/246	medium · avg 60%	▇▇ 4.0%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	51.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 140/246	medium · avg 44%	▇ 1.5%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	79.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 154/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	73.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 155/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	90.7% ✎	▁···▁▁▁▁▃▆█▃ beats 159/246	easy · avg 84%	▇ 0.7%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 176/246	easy · avg 66%	▇ 0.6%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ACOS (per-review F1) submitted	16.0% ✎	▁··▂▃▃▅▇█▇▃▃ beats 84/246	hard · avg 22%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #83 of 247 · 6.9% of its score · 6 tests

Beats Jev 1.13, jev-brain · Gemma-4-31B (decision readout), Jeffan-4B-2010 here, though they rank higher overall. Trails 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: New Yorker (accuracy) submitted	62.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 113/246	medium · avg 61%	▇ 3.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	63.8% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 188/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	91.7% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 164/246	easy · avg 83%	▇ 1.3%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	56.6% ✎	▁········▁▇█ beats 60/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	25.5% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 139/237	hard · avg 21%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	54.4% ✎	▁▂▄█▇▅▁▃▄▄▁▁ beats 184/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▃▃▃▅▅▆█▂ #204 of 263 · 44% of its score · 19 tests

Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, Strands Decider 2B (Hobson v21) 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	29.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 63/246	medium · avg 46%	▇▇▇ 6.7%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	51.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 62/246	easy · avg 70%	▇▇ 6.2%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	70.2% ✎	▂▂▂▂▃▂▁▃▄▆█▆ beats 53/246	very easy · avg 90%	▇▇ 6.0%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	50.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 63/246	easy · avg 66%	▇▇ 5.2%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	85.6% ✎	▁▁▂▁▂▃▂▂▃▆█▅ beats 53/246	very easy · avg 96%	▇▇ 4.0%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	80.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 127/246	easy · avg 78%	▇ 2.9%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	19.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 29/246	medium · avg 45%	▇ 2.2%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	32.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 72/246	medium · avg 39%	▇ 2.0%	blunt · at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	66.0% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 10/25	easy · avg 69%	▇ 1.7%	at its level
Ollaya · BoolQ	78.7% ✎	▁··▃▃▁▄▁▃█▇▄ beats 7/25	easy · avg 84%	▇ 1.5%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	58.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 122/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	31.6% ✎	██▄▃▃▄▁▁···▁ beats 8/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	71.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 131/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	25.4% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 107/246	hard · avg 22%	▇ 0.7%	typical
Ollaya · SQuAD 2 answerability	78.3% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 14/25	easy · avg 80%	▇ 0.7%	blunt
Ollaya · VitaminC verification	77.0% ✎	▁···▃·▄█▃··▁ beats 14/25	easy · avg 78%	▇ 0.7%	blunt · at its level
Ollaya · MultiNLI	83.3% ✎	▂··▄██▂▆▆█▆▂ beats 9/25	very easy · avg 87%	▇ 0.4%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	18.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 152/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 206/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▂▃▆█▄▁▁ #77 of 114 · 11% of its score · 9 tests

Beats Open-Jev-2B (DecisionBench 0c7aa498) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	50.6% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 6/22	medium · avg 64%	▇ 2.7%	at its level
Ollaya · PAWS paraphrase	78.0% ✎	▂▂▂▂·▃█▆·▂·▁ beats 9/25	easy · avg 81%	▇ 1.8%	typical
Ollaya · MASSIVE German intent	79.4% ✎	▁····▁·▂▃▆█▃ beats 9/23	easy · avg 84%	▇ 1.7%	sharp
Ollaya · Aegis 2 safety	82.4% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 22/25	easy · avg 77%	▇ 1.5%	at its level
Ollaya · SummEval relevance	16.3% ✎	▁··▁▃▁▅··▃██ beats 3/25	medium · avg 41%	▇ 1.3%	at its level
Ollaya · SummEval consistency	78.5% ✎	▁·▁▁··▁▁▁▁▄█ beats 12/25	easy · avg 75%	▇ 0.9%	sharp · at its level · noisy
Ollaya · MASSIVE English intent	85.1% ✎	▁·······▂▃█▃ beats 13/23	very easy · avg 86%	▇ 0.9%	noisy
Ollaya · HelpSteer 2 scoring	35.7% ✎	▁▁··▁·▁▃▇█▅▄ beats 10/23	medium · avg 38%	▇ 0.5%	blunt · at its level

1 more test

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Civil Comments	89.7% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 17/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 5.6% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	41.5900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 105/247	avg 41.206 points	▇ 3.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	15.6400 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 60/247	avg 38.861 points	▇ 2.0%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 2.7 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run gliclass:v4-edge --preset triage "The customer requests a refund."

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A matching Ollaya runtime manifest and published short-workload GPU memory measurement were reviewed separately; see local variants and identity_note. The command was not executed in this review. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/knowledgator ↗

$ how the score was worked out · Decision Index 0.4.1 83%, Ollaya · original runs 16%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%	CC BY 4.0
Ollaya · original runs	14	▇▇▇▇▇ 16%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 44.6

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	68.2%	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]	60.1%	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