whatmodel.sh / decision / JEV FLAN-T5 Large public v2 (342M)

JEV FLAN-T5 Large public v2 (342M)

+ contribute

JEV FLAN-T5 Large public v2 (342M) is an open-weights decision model from Elfsong, released 18 October 2026.

Catalogue identity notes

Exact Decision Index tested engine jev-t5-342m-public-v2; reported model JEV FLAN-T5 Large public v2 (342M). 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

Release date ↗

32.1±1.1#297 of 355 decision modelsfrom 41 benchmark results across 1 source

$ how it compares

The decision models ranked either side of JEV FLAN-T5 Large public v2 (342M), out of 357 with a score, then more from Elfsong.

#	model	score	where	released
297	Laya (english) (JevBench mini) Convai Innovations	33±2	source code
298	Kodiak v0.2 1B (accuracy) Cortex Agent LLC	32±1	model files
299	JEV FLAN-T5 Large public v2 (342M) Elfsong	32±1	model files	2026-10-18
300	Verdict 1.4 (JevBench mini) Heman10x	32±2	source code
301	Crivo-150M v2 tardellirs	32±1	model files
	more from Elfsong
287	JEV Ettin 150M Elfsong	34±1	model files	2026-10-23
319	JEV Ettin 400M Elfsong	29±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #235 of 250 · 7.8% of its score · 5 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	38.8% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 12/246	very easy · avg 92%	▇▇ 5.7%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	58.7% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 63/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	39.1% ✎	▁▁▁▁▁·▃▁▁▄█▁ beats 17/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 10/243	medium · avg 37%	▇ 0.2%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	62.5% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #231 of 258 · 4.8% of its score · 7 tests

Beats Sieve 2B, Strands Decider 2B (Hobson v21), Valen-0.8B 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	27.1% ✎	▁▁▁▁▁▁▃▂▃▃█▅ beats 23/246	medium · avg 47%	▇ 1.4%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	25.8% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 33/246	medium · avg 38%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	76.8% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 55/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	62.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 65/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.2% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 33/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	75.4% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 67/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	46.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #185 of 256 · 24% of its score · 9 tests

Beats Nari Decision 4B v3.2, Solar Decide Flash, Lev1 3.7B here, though they rank higher overall. Trails DecisionTune 1.0, vera-spark 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	77.3% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 74/246	very easy · avg 85%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	57.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 34/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	49.2% ✎	▁▂▃▅▅█▂····▁ beats 62/246	medium · avg 60%	▇▇ 4.0%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	29.9% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 60/246	medium · avg 44%	▇ 1.2%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	55.5% ✎	▁▁▁▁▁▁▁▃▂▇▇█ beats 41/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	81.0% ✎	▁···▁▁▁▁▃▆█▃ beats 74/246	easy · avg 84%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	51.9% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 81/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	51.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 48/246	easy · avg 66%	▇ 0.7%	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	10.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 59/246	hard · avg 22%	▇ 0.4%	noisy

arts & human taste▃▇▄▃▅▅█▅▄▂▁▁ #246 of 247 · 7.4% of its score · 6 tests

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	45.5% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 49/246	medium · avg 61%	▇ 3.1%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	39.4% ✎	▃█▄▄▅█▆▅▄▁▁▁ beats 1/246	easy · avg 83%	▇ 1.8%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	56.7% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 67/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	52.5% ✎	▁········▁▇█ beats 42/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	32.4% ✎	▁▃▄█▇▅▁▁▄▄▁▁ beats 6/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	0.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 4/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▃▂▃▃▅▅▆█▂ #226 of 263 · 50% 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, InternLM Intern-Decision Qwen3.5-0.8B 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	74.9% ✎	▁▁▂▁▃▂▂▂▃▆█▅ beats 36/246	very easy · avg 96%	▇▇▇▇ 11%	sharp · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	58.4% ✎	▂▂▂▃▂▂▁▃▄▆█▆ beats 40/246	very easy · avg 90%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	40.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 34/246	easy · avg 70%	▇▇▇ 6.8%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	40.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 38/246	easy · avg 66%	▇▇ 5.4%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	16.6% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 27/246	medium · avg 46%	▇▇ 5.1%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	70.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 87/246	easy · avg 78%	▇ 3.6%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	26.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 31/246	medium · avg 39%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	18.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 23/246	medium · avg 45%	▇ 1.6%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	56.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 98/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	56.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 52/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	44.2% ✎	██▄▃▃▄▁▁···▁ beats 81/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	17.0% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 62/246	hard · avg 22%	▇ 0.5%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	7.9% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 22/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	14.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 187/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 5.8% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	18.9400 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 35/247	avg 41.206 points	▇ 3.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	14.8600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 55/247	avg 38.861 points	▇ 2.1%	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	41	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 32.1

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	62.5%	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]	46.4%	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