Lev1 3.7B

+ contribute

Lev1 3.7B is an open-weights decision model from theaviv, released 4 October 2026. Its published size is 3.7B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine lev1-3.7b; reported model Lev1 3.7B. Type: LoRA; technique: autoregressive. 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 ↗ · Weights licence ↗ · Parameter count ↗

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

47.2±1.2#228 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Lev1 3.7B, out of 357 with a score.

#	model	score	where	released
228	RSI-Jev v5.0 VL 3B shgao	48±1	model files	2026-10
229	Sieve 2B v3 Sthānika AI	48±1	model files
230	Lev1 3.7B theaviv	47±1	model files	2026-10-04
231	Ryotide Qwen v0.3.1 (decision readout) csabag	47±1	source code
232	decider-2b v10 (JevBench mini) Mapika	47±2	source code

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #131 of 250 · 8.3% of its score · 6 tests

Beats Tern-35B-A3B, Cerno 4B v1.1, Trio-Spark DI (9B) here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B 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)	94.1% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 118/246	very easy · avg 92%	▇ 3.0%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy)	80.1% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 117/236	easy · avg 70%	▇ 2.5%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy)	86.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 179/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10)	63.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 109/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy)	26.1% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 98/243	medium · avg 37%	▇ 0.8%	sharp · at its level · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective))	79.3% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #184 of 258 · 5.8% of its score · 7 tests

Beats JevK5 9B v0.3.3, JevK5 v0.3, Hopper (G) 1.2 Qwen3.5-4B LoRA here, though they rank higher overall. Trails Mola-68M, Bosun v3.1 1.7B LoRA, Dinah-1 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)	44.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 142/246	medium · avg 38%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1)	42.4% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 72/246	medium · avg 47%	▇ 1.9%	at its level
Decision Index 0.4.1: HoVer (accuracy)	65.1% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 81/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy)	50.5% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 36/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1)	92.3% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 162/238	easy · avg 83%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1)	80.9% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 107/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1)	67.1% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #187 of 256 · 24% of its score · 9 tests

Beats Nari Decision 4B v3.2, Solar Decide Flash 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)	76.3% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 66/246	very easy · avg 85%	▇▇▇ 7.2%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1)	75.8% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 104/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1)	55.4% ✎	▁▂▃▅▅█▂····▁ beats 83/246	medium · avg 60%	▇▇ 4.9%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English)	38.2% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 84/246	medium · avg 44%	▇ 1.9%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1)	78.3% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 145/246	easy · avg 71%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1)	46.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 65/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: ACOS (per-review F1)	15.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 80/246	hard · avg 22%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class)	73.7% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 120/246	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: FinEntity (macro-F1)	83.2% ✎	▁···▁▁▁▁▃▆█▃ beats 89/246	easy · avg 84%	▇ 0.8%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #154 of 247 · 8.6% of its score · 6 tests

Beats Jegue 0.1 (9B), Standard One 8B SH (v4), Sieve 4B here, though they rank higher overall. Trails Crivo-32M v2, Crivo-68M, Crivo-150M v2 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)	65.5% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 130/246	medium · avg 61%	▇ 3.7%	at its level
Decision Index 0.4.1: Humicroedit (accuracy)	63.0% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 169/246	medium · avg 60%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy)	81.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 92/246	easy · avg 83%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy)	56.6% ✎	▁········▁▇█ beats 61/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy)	14.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 120/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy)	43.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 113/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #179 of 263 · 46% of its score · 14 tests

Beats baselabs joey-1 (2B), Aurelis-2B, StartLux-Decision v1.1 0.8B here, though they rank higher overall. Trails mini-jev Qwen3-4B (decision readout), Cam1, openvons Qwen3-4B (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)	37.9% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 79/246	medium · avg 46%	▇▇▇ 8.7%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy)	67.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 86/246	easy · avg 70%	▇▇▇ 7.4%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy)	61.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 89/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy)	88.5% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 85/246	very easy · avg 90%	▇▇▇ 6.3%	sharp
Decision Index 0.4.1: ARC-Easy (accuracy)	94.2% ✎	▁▁▂▁▂▂▂▃▃▆█▅ beats 79/246	very easy · avg 96%	▇▇ 3.9%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy)	70.6% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 88/246	easy · avg 78%	▇ 3.4%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice))	28.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 71/246	medium · avg 45%	▇ 2.9%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy)	32.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 65/246	medium · avg 39%	▇ 2.6%	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)	62.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 150/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy)	51.9% ✎	██▄▃▃▄▁▁···▁ beats 119/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy)	24.0% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 100/246	hard · avg 22%	▇ 1.0%	typical
Decision Index 0.4.1: CLadder (accuracy)	59.8% ✎	▁███▆▅▃▃▁▁▁▁ beats 63/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: ChessBench (accuracy)	15.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 113/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy)	9.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 21/246	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)	40.8800 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 101/247	avg 41.206 points	▇▇ 4.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	27.2100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 91/247	avg 38.861 points	▇ 2.5%	blunt

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. 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/theaviv ↗

$ 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	42	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 47.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.3%	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]	67.1%	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