whatmodel.sh / decision / GLiNER2.5-Decide

GLiNER2.5-Decide

+ contribute

GLiNER2.5-Decide is an open-weights decision model from Fastino. Its published size is 0.49B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine gliner-decide; reported model GLiNER2.5-Decide. Type: full fine-tune; technique: GLiNER2. Implementation: https://github.com/fastino-ai/GLiNER2. 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.

22.9±1.0#334 of 355 decision modelsfrom 48 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of GLiNER2.5-Decide, out of 357 with a score, then more from Fastino.

#	model	score	where	released
334	Bekko System One v0 68M hotchpotch	24±1	model files
335	MoganAI Lavoir ModernBERT-large Mogan AI	24±1	model files
336	GLiNER2.5-Decide Fastino	23±1	model files
337	Prumo (rule-based engine) tardellirs	23±1	source code
338	gliner2.5-small-v1 (DecisionBench 7e6f537f) Fastino	23±2	model files
	more from Fastino
4	Fastino GLiDE 1.2 Fastino	73±1	model files	2026-10-22
313	GLiNER2.5-Decide (DecisionBench 0872ab14) Fastino	30±2	model files
326	gliner2-large-v1 (DecisionBench f32ea6ef) Fastino	26±2	model files

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

$ what it's good at

tools & automation▁▃▃▁▁▂▃▄▆██▆ #231 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1, JEV FLAN-T5 Large public v2 (342M), Bekko System One v0 400M here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Prumo (rule-based engine) 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	46.2% ✎	▁▂▃▁▁▂▂▄▅▆█▁ beats 19/246	very easy · avg 92%	▇▇▇ 6.7%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	7.7% ✎	▁▁▁▁▃▁▁▂▃▂█▂ beats 14/236	easy · avg 70%	▇ 1.7%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	33.4% ✎	▁▁▁▃▃▅▅▆█▇█▃ beats 18/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	38.2% ✎	▁▁▁▁▁·▃▁▁▄█▁ beats 16/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 33/243	medium · avg 37%	▇ 0.1%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	59.4% ✎	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▁▁▁·▁▃▁▁▃▃█▅ #244 of 258 · 4.4% of its score · 7 tests

Beats DM-JEPA 1.1, Together Tev1 Qwen3.5-0.8B, LFM2.5-2.6B-RLCD here, though they rank higher overall. Trails Laya, Prumo (rule-based engine) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	23.3% ✎	▁▁▁▁▁▃▂▂▃▃█▅ beats 15/246	medium · avg 47%	▇ 1.2%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	20.1% ✎	▁▁▁▁▁▃▁▂▂▄▇█ beats 18/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	60.4% ✎	▁▁▁▁▁▁▁▃▃▆█▄ beats 33/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	50.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 10/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 15/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	65.6% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 33/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	0.8% ✎	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▃▂▂▃▂▅▆▃█▆▄▃ #248 of 256 · 23% of its score · 9 tests

Beats Crivo-17M here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads, jeff GLiFormer-large (decision readout), Verdict 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	32.2% ✎	▃▄▂▂▄▇▃▇█▅▃▁ beats 8/246	very easy · avg 85%	▇▇▇▇ 9.2%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	48.0% ✎	▁▁▁▃▂▃▃▄▇▇█▄ beats 10/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	30.9% ✎	▁▃▃▅▅█▂····▁ beats 17/246	medium · avg 60%	▇ 3.5%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	66.2% ✎	▁···▁▁▁▁▃▆█▃ beats 35/246	easy · avg 84%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	32.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 67/246	medium · avg 44%	▇ 1.0%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	21.8% ✎	▁▁▁▃▁▁▁▂▂▇▇█ beats 10/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	35.3% ✎	▁▁▁▃▅▄▄▂▄▆█▄ beats 16/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	25.3% ✎	▁▁▁▁▁▁▁▃▁▃▆█ beats 25/246	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	0.0% ✎	▃··▂▃▃▅▇█▇▃▃ beats 1/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #199 of 247 · 7.0% of its score · 6 tests

Beats vLLM-SR d3-nano (2B), Valen-4B, Saracura PT-BR 4B here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout) 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	32.2% ✎	▁▁▃▃▃▃▇▅█▅▃▁ beats 21/246	medium · avg 61%	▇ 2.7%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	58.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 47/246	easy · avg 83%	▇ 1.9%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	50.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 23/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	53.4% ✎	▁········▁▇█ beats 47/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	45.5% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 140/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.7% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 40/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #250 of 263 · 49% of its score · 14 tests

Beats Amber 0.4B, Crivo-32M v2, Crivo-17M here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads, Qwen-2.5-1B-RLCD (decision readout) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	54.1% ✎	▁▁▃▁▂▂▂▂▃▆█▅ beats 14/246	very easy · avg 96%	▇▇▇▇▇▇ 15%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	36.8% ✎	▂▃▂▂▂▂▁▃▄▆█▆ beats 15/246	very easy · avg 90%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	33.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 16/246	easy · avg 70%	▇▇ 5.8%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	31.1% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 3/246	easy · avg 66%	▇▇ 4.7%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	50.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 12/246	easy · avg 78%	▇ 3.7%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	16.1% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 23/246	medium · avg 46%	▇ 3.6%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	21.4% ✎	▃▆▅▅▆█▆▃▁··▁ beats 3/246	medium · avg 39%	▇ 1.6%	blunt
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	17.3% ✎	▁··▄█▆▆▆▅▅▃▁ beats 6/246	medium · avg 45%	▇ 1.1%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	45.2% ✎	▁▃▂█▅▄▁▁▁▁▁▁ beats 21/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	50.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 11/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	40.2% ✎	██▄▃▃▄▁▁···▁ beats 58/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	0.7% ✎	▃▁▁▁▁▁▁▂▅█▂▁ beats 13/246	hard · avg 22%	▇ 0.4%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.1% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 25/246	hard · avg 16%	▇ 0.2%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	16.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 229/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▁▁▁▂▁▃▂▆█▄▁▁ #89 of 114 · 0.9% of its score · 6 tests

Beats kev-0.6b (DecisionBench dece6dba), mojev (DecisionBench 0c8695b6), smalljev-semantic-v9 (DecisionBench 8e2bac7c) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Perch semantic lint · private (Youden J)	0.0000 J ✎	█····▄█▄···█ beats 0/7	avg 0.380 J	▇ 0.3%	blunt
Perch semantic lint · public (Youden J)	0.0000 J ✎	█····▄█▄···█ beats 0/7	avg 0.363 J	▇ 0.3%	blunt
Perch security detection · public (Youden J)	0.0055 J ✎	█···▄▄···▄▄█ beats 1/7	avg 0.052 J	▇ 0.1%	blunt
Perch bug detection · private (Youden J)	-0.0045 J ✎	▅··▃▃█·····▃ beats 1/7	avg 0.027 J	▇ 0.1%	blunt
Perch bug detection · public (Youden J)	0.0022 J ✎	█▄·█·▄▄····▄ beats 0/7	avg 0.026 J	▇ 0.0%	blunt
Perch security detection · private (Youden J)	0.0055 J ✎	█▃▃··▃·▃···▃ beats 2/7	avg 0.017 J	▇ 0.0%	blunt

other tests2 not in a task · 5.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	11.1400 points ✎	▂▃▂▃▃▃▄▅▅▇█▃ beats 15/247	avg 41.206 points	▇ 3.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	8.6400 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 11/247	avg 38.861 points	▇ 2.0%	blunt

$ where to run it

Download model files ↗
Published model files verified. 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/fastino ↗

$ how the score was worked out · Decision Index 0.4.1 99%, Perch benchmark results 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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
Perch benchmark results	6	▇ 1%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 22.9

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	59.4%	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]	0.8%	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