whatmodel.sh / decision / JEV Ettin 400M

JEV Ettin 400M

+ contribute

JEV Ettin 400M is an open-weights decision model from Elfsong. Its published size is 0.4B parameters.

Catalogue identity notes

Exact Decision Index tested engine jev-ettin-400m; reported model JEV Ettin 400M. Type: full fine-tune; technique: encoder. 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

· Parameter count ↗

Publisher parameter count (estimated by publisher); includes the served backbone, not just adapter size.

28.5±1.0#317 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of JEV Ettin 400M, out of 357 with a score, then more from Elfsong.

#	model	score	where	RAM	released
317	vLLM-SR Decision 2.0 Kai 0.6B vLLM Semantic Router	29±1	local	~3.7GB
318	Mola-68M codavidgarcia	29±1	model files		2026-10-14
319	JEV Ettin 400M Elfsong	29±1	model files
320	ZTC-Judge-4B (DecisionBench b0bb1603) FINAL-Bench	29±2	model files
321	Jev-Style 0.8B v3 chaoliangUNSW	28±1	model files		2026-09-24
	more from Elfsong
287	JEV Ettin 150M Elfsong	34±1	model files		2026-10-23
299	JEV FLAN-T5 Large public v2 (342M) Elfsong	32±1	model files		2026-10-18

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #236 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1 here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Prumo (rule-based engine), GLiNER2.5-Decide 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	38.9% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 14/246	very easy · avg 92%	▇▇ 6.2%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	25.3% ✎	▁▁▁▁▁▁▃▂▃▂█▂ beats 20/236	easy · avg 70%	▇ 1.9%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	17.0% ✎	▁▃▁▂▃▅▅▆█▇█▃ beats 4/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	40.0% ✎	▁▁▁▁▁·▃▁▁▄█▁ beats 19/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 8/243	medium · avg 37%	▇ 0.2%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	61.8% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #227 of 258 · 4.5% of its score · 7 tests

Beats EXAONE-4.0-1.2B-JEV v0.3, Sieve 2B, Strands Decider 2B (Hobson v21) here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Jev-Style 0.8B v3 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	29.6% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 34/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	23.7% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 29/246	medium · avg 38%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	51.3% ✎	▁▁▁▁▁▁▁▃▃▆█▄ beats 28/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	56.6% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 30/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	52.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 58/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	56.1% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 18/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	43.2% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #219 of 256 · 23% of its score · 9 tests

Beats wyat-1-800m, Valen-0.8B, JPT-0.8B Qwen3.5-0.8B LoRA here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: HellaSwag (accuracy) submitted	55.7% ✎	▂▄▃▂▄▇▃▇█▅▃▁ beats 37/246	very easy · avg 85%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	55.0% ✎	▁▁▁▂▃▃▃▄▇▇█▄ beats 25/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	38.2% ✎	▁▂▃▅▅█▂····▁ beats 31/246	medium · avg 60%	▇ 3.7%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	26.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 40/246	medium · avg 44%	▇ 1.1%	typical
Decision Index 0.4.1: FinEntity (macro-F1) submitted	44.1% ✎	▁···▁▁▃▁▃▆█▃ beats 14/246	easy · avg 84%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	33.0% ✎	▁▁▁▁▃▁▁▂▂▇▇█ beats 21/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	46.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 64/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	51.8% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 50/246	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	8.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 44/246	hard · avg 22%	▇ 0.3%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #221 of 247 · 7.1% of its score · 6 tests

Beats Valen-4B, TokenRhythm NeoHorse-Jev-4B, OneJev1.6-0.8B here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Bekko System One v0 17M 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	42.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 41/246	medium · avg 61%	▇ 2.8%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	51.0% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 26/246	easy · avg 83%	▇ 1.8%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	51.3% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 33/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	47.9% ✎	▁········▃▇█ beats 3/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	28.2% ✎	▃▂▄█▇▅▁▁▄▄▁▁ beats 0/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	2.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 51/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▃▂▃▃▅▅▆█▂ #227 of 263 · 49% of its score · 14 tests

Beats Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326), Amber 0.4B, vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B) here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), LFM2.5-2.6B-RLCD 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	76.0% ✎	▁▁▂▁▃▂▂▂▃▆█▅ beats 38/246	very easy · avg 96%	▇▇▇▇▇ 13%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	56.0% ✎	▂▂▂▃▂▂▁▃▄▆█▆ beats 35/246	very easy · avg 90%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	41.4% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 38/246	easy · avg 70%	▇▇▇ 6.3%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	40.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 39/246	easy · avg 66%	▇▇ 5.0%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	18.6% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 36/246	medium · avg 46%	▇▇ 4.4%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	59.6% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 44/246	easy · avg 78%	▇ 3.6%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	23.0% ✎	▃▆▅▅▆█▆▃▁··▁ beats 7/246	medium · avg 39%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	20.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 37/246	medium · avg 45%	▇ 1.3%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	53.5% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 48/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	57.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 56/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	40.2% ✎	██▄▃▃▄▁▁···▁ beats 54/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	6.2% ✎	▁▁▁▁▁▃▁▂▅█▂▁ beats 37/246	hard · avg 22%	▇ 0.4%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	6.6% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 0/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 212/246	very hard · avg 13%	▇ 0.0%	blunt

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)	13.9400 points ✎	▂▂▃▃▃▃▄▅▅▇█▃ beats 23/247	avg 41.206 points	▇ 3.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	17.1900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 66/247	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/Elfsong ↗

$ how the score was worked out · Decision Index 0.4.1 100%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 28.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	61.8%	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]	43.2%	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