Metask-Jev-4B

+ contribute

Metask-Jev-4B is an open-weights decision model from Metask-AI-Lab. Its published size is 4.66B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine metask-jev-4b; reported model Metask-Jev-4B. Type: LoRA; technique: autoregressive. Implementation: https://github.com/metask-ai/metask-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.

45.0±1.2#242 of 355 decision modelsfrom 38 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Metask-Jev-4B, out of 357 with a score.

#	model	score	where	released
242	SemIf Qwen3.5-4B Base (decision readout) TheoLeeCJ	46±1	source code
243	RSI-Jev v3.0 2B (JevBench mini) Shanghua Gao	45±2	source code
244	Metask-Jev-4B Metask-AI-Lab	45±1	model files
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

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #187 of 250 · 6.3% of its score · 5 tests

Beats JevK5 v0.3, FlyMy.AI Decision 4B v1.6, RSI-Jev v5.0 VL 3B here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Mola-150M 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	86.7% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 62/246	very easy · avg 92%	▇ 3.5%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	42.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 30/246	easy · avg 72%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 153/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	20.4% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 89/243	medium · avg 37%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.6% ✎	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▁▁▁·▁▁▁▃▃▃█▅ #211 of 258 · 4.9% of its score · 5 tests

Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Mola-68M 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	40.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 97/246	medium · avg 38%	▇ 1.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	34.9% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 46/246	medium · avg 47%	▇ 1.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	62.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 66/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	51.6% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 52/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	57.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #191 of 256 · 25% of its score · 9 tests

Beats Nari Decision 4B v3.2, Solar Decide Flash, TokenRhythm NeoHorse-Jev-4B here, though they rank higher overall. Trails DecisionTune 1.0, vera-spark, JEV FLAN-T5 Large public v2 (342M) 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	75.3% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 63/246	very easy · avg 85%	▇▇▇ 8.0%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	73.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 89/246	easy · avg 74%	▇▇ 5.6%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	56.3% ✎	▁▂▃▅▅█▂····▁ beats 91/246	medium · avg 60%	▇▇ 5.0%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	47.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 123/246	medium · avg 44%	▇ 1.9%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	69.3% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 70/246	easy · avg 71%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	43.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 45/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	79.3% ✎	▁···▁▁▁▁▃▆█▃ beats 66/246	easy · avg 84%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	66.4% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 84/246	easy · avg 66%	▇ 0.8%	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	6.8% ✎	▁··▂▃▃▅▇█▇▃▃ beats 35/246	hard · avg 22%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #162 of 247 · 8.2% of its score · 5 tests

Beats Jegue 0.1 (9B), Standard One 8B SH (v4), PurpleMIST-Flash-1.0 here, though they rank higher overall. Trails Crivo-17M, Crivo-32M v2, Crivo-68M 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	55.3% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 73/246	medium · avg 61%	▇▇ 3.8%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	52.1% ✎	▁·▁▃▃▂▅█▄▂▁▁ beats 39/246	medium · avg 60%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	78.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 85/246	easy · avg 83%	▇ 1.5%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	57.9% ✎	▁········▁▇█ beats 75/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 66/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #166 of 263 · 48% of its score · 14 tests

Beats StartLux-Decision v1.1 2B, Solomon v1.1, Standard One 3B SH (v4) here, though they rank higher overall. Trails Jevstral 8B, Jobe Qwen3.5-4B (decision readout) 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	45.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 98/246	medium · avg 46%	▇▇▇ 8.5%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	69.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 96/246	easy · avg 70%	▇▇▇ 7.7%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	89.9% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 96/246	very easy · avg 90%	▇▇▇ 7.3%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	60.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 83/246	easy · avg 66%	▇▇▇ 6.5%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	95.4% ✎	▁▁▂▁▂▂▂▃▃▆█▅ beats 85/246	very easy · avg 96%	▇▇ 4.8%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	67.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 66/246	easy · avg 78%	▇ 3.5%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	27.4% ✎	▁··▄█▆▆▆▅▅▃▁ beats 68/246	medium · avg 45%	▇ 2.8%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	40.8% ✎	▂▆▅▅▆█▆▃▁··▁ beats 116/246	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	54.8% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 63/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	46.3% ✎	██▄▃▃▄▁▁···▁ beats 94/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	61.7% ✎	▁███▆▅▃▃▁▁▁▁ beats 69/246	easy · avg 71%	▇ 1.0%	at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	17.1% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 63/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	23.1% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 202/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	8.4% ✎	▁▃▂▃▆█▇▅▅▃▁▁ beats 5/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 7.1% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	27.0900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 58/247	avg 41.206 points	▇▇ 4.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	39.7900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 127/247	avg 38.861 points	▇ 2.5%	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/wayfind ↗

$ 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	38	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 45.0

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.6%	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]	57.6%	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