Verdict

+ contribute

Verdict is an open-weights decision model from heman10x. Its published size is 0.15B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine verdict-8af2496e; reported model Verdict. Type: full fine-tune; technique: GLiClass. Implementation: https://github.com/Heman10x-NGU/Verdict-open-jev. 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.

21.0±1.1#339 of 355 decision modelsfrom 37 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Verdict, out of 357 with a score, then more from heman10x.

#	model	score	where	RAM
339	Qwen-2.5-1B-RLCD (decision readout) harshatheg	21±1	source code
340	Laya ConvAI Innovations	21±1	model files
341	Verdict heman10x	21±1	model files
342	jeff GLiFormer-large (decision readout) logan-markewich	21±1	source code
343	CLM-v0.1-8B Qwen3-8B heads Contrastive-LM	20±1	local	~15GB
	more from heman10x
327	rlcd-modernbert-151m (DecisionBench 8af2496e) heman10x	26±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #238 of 250 · 8.9% of its score · 4 tests

Beats DM-JEPA 1.1, LFM2.5-2.6B-RLCD, Von 1.3 here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads 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	38.8% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 13/246	very easy · avg 92%	▇▇▇ 7.1%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	36.8% ✎	▁▁▁▃▃▅▅▆█▇█▃ beats 21/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	19.0% ✎	▁▁▁▃▁·▁▁▁▄█▁ beats 11/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	50.8% ✎	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▁▁▃·▁▁▁▁▃▃█▅ #254 of 258 · 3.6% of its score · 5 tests

Beats JevK5 Lite, Qwen-2.5-1B-RLCD (decision readout) here, though they rank higher overall. Trails Zev (decision readout), Nirnaya 0.4B, Supersonic Labs Julia 1 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	12.8% ✎	▁▁▁▃▁▁▂▂▃▃█▅ beats 5/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	9.0% ✎	▃▁▁▁▁▁▁▂▂▄▇█ beats 2/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: HoVer (accuracy) submitted	51.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 14/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	55.3% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 72/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	7.9% ✎	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▂▃▂▃▂▅▆▃█▆▄▃ #243 of 256 · 23% of its score · 9 tests

Beats Crivo-32M v2, Bosun v3.1 0.6B LoRA, Crivo-17M here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads 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	35.1% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 14/246	very easy · avg 85%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	51.5% ✎	▁▁▁▂▃▃▃▄▇▇█▄ beats 22/246	easy · avg 74%	▇▇ 5.8%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	14.9% ✎	▃▂▃▅▅█▂····▁ beats 0/246	medium · avg 60%	▇ 3.6%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	42.1% ✎	▁···▁▁▃▁▃▆█▃ beats 12/246	easy · avg 84%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	21.2% ✎	▁▁▁▃▁▁▁▂▂▇▇█ beats 7/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	10.1% ✎	▁·▁·▁▃▂▄▅█▇▄ beats 7/246	medium · avg 44%	▇ 1.0%	typical
Decision Index 0.4.1: VAST (macro-F1) submitted	33.4% ✎	▁▁▁▃▅▄▄▂▄▆█▄ beats 11/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	11.9% ✎	▁▁▁▁▁▃▁▁▁▃▆█ beats 13/246	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	3.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 16/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #242 of 247 · 7.2% of its score · 5 tests

Beats JEV Ettin 150M, JEV FLAN-T5 Large public v2 (342M), Kev 0.8B r15 here, though they rank higher overall. Trails Zev (decision readout), LFM2.5-350M-RLCD, Nirnaya 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	80.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 220/246	medium · avg 61%	▇ 2.7%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	47.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 4/246	easy · avg 83%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	38.6% ✎	▃·▁▃▂▂▅█▄▂▁▁ beats 0/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.6% ✎	▁········▁▇█ beats 196/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	37.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 36/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #253 of 263 · 50% of its score · 14 tests

Beats Crivo-32M v2, Crivo-17M, Prumo (rule-based engine) here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads, jeff GLiFormer-large (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	52.1% ✎	▁▁▃▁▂▂▂▂▃▆█▅ beats 13/246	very easy · avg 96%	▇▇▇▇▇▇ 16%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	27.4% ✎	▃▂▂▂▂▂▁▃▄▆█▆ beats 5/246	very easy · avg 90%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	30.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 11/246	easy · avg 70%	▇▇ 5.9%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	33.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 10/246	easy · avg 66%	▇▇ 4.8%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	49.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 0/246	easy · avg 78%	▇▇ 3.9%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	13.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 12/246	medium · avg 46%	▇ 3.5%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	28.7% ✎	▂▆▅▅▆█▆▃▁··▁ beats 52/246	medium · avg 39%	▇ 1.7%	blunt
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	3.1% ✎	▃··▄█▆▆▆▅▅▃▁ beats 0/246	medium · avg 45%	▇ 1.0%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	41.0% ✎	▁▃▂█▅▄▁▁▁▁▁▁ beats 13/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	37.9% ✎	▃███▆▅▃▃▁▁▁▁ beats 0/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	39.3% ✎	██▄▃▃▄▁▁···▁ beats 50/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	1.2% ✎	▁▃▁▁▁▁▁▂▅█▂▁ beats 16/246	hard · avg 22%	▇ 0.3%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	17.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 139/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 196/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.1% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	1.3800 points ✎	▃▂▂▃▃▃▄▅▅▇█▃ beats 2/247	avg 41.206 points	▇▇ 3.9%	blunt
Decision Index 0.4.1: private new domains (equated points)	3.0400 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 0/247	avg 38.861 points	▇ 2.2%	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/heman10x ↗

$ 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	37	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 21.0

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	50.8%	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]	7.9%	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