whatmodel.sh / decision / Supersonic Labs Julia 1

Supersonic Labs Julia 1

+ contribute

Supersonic Labs Julia 1 is an open-weights decision model from Supersonic Labs, released 25 September 2026. Its published size is 0.14B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine julia-1; reported model Supersonic Labs Julia 1. 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 ↗ · Weights licence ↗ · Parameter count ↗

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

18.4±0.9#348 of 355 decision modelsfrom 50 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Supersonic Labs Julia 1, out of 357 with a score.

#	model	score	where	released
348	bge-reranker-v2-m3 (DecisionBench 953dc6f6) BAAI	19±2	model files
349	system-one-gemma akash-kamat	18±1	source code
350	Supersonic Labs Julia 1 Supersonic Labs	18±1	model files	2026-09-25
351	KaLM-Reranker-V1-Small-R2 (DecisionBench d1c8fdf9) KaLM-Embedding	18±2	model files
352	KaLM-Reranker-V1-Nano-R2 (DecisionBench 3902d645) KaLM-Embedding	17±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #244 of 250 · 16% of its score · 8 tests

Beats Von 1.3, jeff GLiFormer-large (decision readout), Bekko System One v0 17M here, though they rank higher overall. Trails LFM2.5-350M-RLCD here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecideBench v1: agent routing	40.0% ✎	▄·····▂▄·█·▄ beats 1/10	very easy · avg 93%	▇▇ 6.0%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	37.5% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 7/246	very easy · avg 92%	▇▇ 5.2%	sharp · at its level · noisy
DecideBench v1: action review	38.0% ✎	▃▃·▃·█···█·▅ beats 0/10	easy · avg 87%	▇ 2.3%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	18.3% ✎	▁▁▁▁▁▃▁▂▃▂█▂ beats 16/236	easy · avg 70%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	23.6% ✎	▁▁▃▂▃▅▅▆█▇█▃ beats 11/246	easy · avg 72%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	13.6% ✎	▁▃▁▁▁·▁▁▁▄█▁ beats 6/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 22/243	medium · avg 37%	▇ 0.0%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	57.6% ✎	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▁▁▁·▃▁▁▁▃▃█▅ #249 of 258 · 6.2% of its score · 8 tests

Beats DM-JEPA 1.1, JevK5 Lite, Qwen-2.5-1B-RLCD (decision readout) here, though they rank higher overall. Trails Nirnaya 0.4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecideBench v1: support intent	54.0% ✎	▃····▂▂·▃··█ beats 1/10	very easy · avg 95%	▇ 2.8%	sharp · at its level · noisy
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	20.6% ✎	▁▁▁▁▁▃▂▂▃▃█▅ beats 9/246	medium · avg 47%	▇ 0.9%	typical
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	9.1% ✎	▃▁▁▁▁▁▁▂▂▄▇█ beats 3/246	medium · avg 38%	▇ 0.9%	blunt
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	12.3% ✎	▁▁▁▁▃▁▁▂▃▆█▄ beats 12/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	50.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 5/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	49.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 9/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	42.6% ✎	▁·▁▁▁▁▁▃▂█▇█ beats 13/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	35.0% ✎	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▃▂▂▃▂▅▆▃█▆▄▃ #251 of 256 · 24% of its score · 12 tests

Beats Prumo (rule-based engine), system-one-gemma 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	29.9% ✎	▃▄▂▂▄▇▃▇█▅▃▁ beats 5/246	very easy · avg 85%	▇▇▇ 6.5%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	49.7% ✎	▁▁▁▃▂▃▃▄▇▇█▄ beats 20/246	easy · avg 74%	▇▇ 4.3%	at its level
DecideBench v1: review sentiment	22.0% ✎	▃··▂···▂▂█▄▂ beats 0/10	easy · avg 85%	▇▇ 4.2%	sharp
Decision Index 0.4.1: ANLI (macro-F1) submitted	28.6% ✎	▁▃▃▅▅█▂····▁ beats 11/246	medium · avg 60%	▇ 2.6%	at its level
DecideBench v1: content moderation	38.0% ✎	▂··▃···▄▄▂·█ beats 1/10	easy · avg 83%	▇ 2.1%	sharp · noisy
DecideBench v1: claim support	24.0% ✎	▄··▄·▄·▄▄███ beats 0/10	easy · avg 82%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	32.8% ✎	▁···▁▁▃▁▃▆█▃ beats 7/246	easy · avg 84%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	31.8% ✎	▁▁▁▁▃▁▁▂▂▇▇█ beats 20/246	easy · avg 71%	▇ 0.7%	at its level · noisy

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	6.5% ✎	▁·▁·▃▁▂▄▅█▇▄ beats 5/246	medium · avg 44%	▇ 0.7%	typical
Decision Index 0.4.1: VAST (macro-F1) submitted	32.9% ✎	▁▁▁▃▅▄▄▂▄▆█▄ beats 10/246	medium · avg 62%	▇ 0.6%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	52.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 56/246	easy · avg 66%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: ACOS (per-review F1) submitted	3.1% ✎	▁··▃▃▃▅▇█▇▃▃ beats 11/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #240 of 247 · 5.3% of its score · 6 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	23.5% ✎	▁▃▂▃▃▃▇▅█▅▃▁ beats 8/246	medium · avg 61%	▇ 1.9%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	48.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 8/246	easy · avg 83%	▇ 1.4%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	48.3% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 9/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	50.4% ✎	▁········▁▇█ beats 21/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	35.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 19/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	0.2% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 7/237	hard · avg 21%	▇ 0.0%	sharp · too hard for it · noisy

knowledge & reasoning▃▂▂▂▂▃▃▅▅▆█▂ #257 of 263 · 36% of its score · 14 tests

Beats Crivo-17M, Prumo (rule-based engine), Bekko System One v0 17M here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	39.1% ✎	▁▃▂▁▂▂▂▂▃▆█▅ beats 4/246	very easy · avg 96%	▇▇▇▇▇ 11%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	32.6% ✎	▂▃▂▂▂▂▁▃▄▆█▆ beats 11/246	very easy · avg 90%	▇▇▇ 7.1%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	30.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 8/246	easy · avg 70%	▇▇ 4.2%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	33.8% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 12/246	easy · avg 66%	▇ 3.4%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	50.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 11/246	easy · avg 78%	▇ 2.9%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	14.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 19/246	medium · avg 46%	▇ 2.3%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	25.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 20/246	medium · avg 39%	▇ 1.2%	blunt
Decision Index 0.4.1: MuSR (accuracy) submitted	39.0% ✎	▃▁▂█▅▄▁▁▁▁▁▁ beats 8/246	medium · avg 60%	▇ 0.7%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: CLadder (accuracy) submitted	50.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 12/246	easy · avg 71%	▇ 0.7%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	16.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 2/246	medium · avg 45%	▇ 0.7%	sharp
Decision Index 0.4.1: CRUXEval (accuracy) submitted	38.1% ✎	██▄▃▃▄▁▁···▁ beats 42/246	medium · avg 58%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	1.0% ✎	▁▃▁▁▁▁▁▂▅█▂▁ beats 14/246	hard · avg 22%	▇ 0.2%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	7.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 13/246	hard · avg 16%	▇ 0.2%	blunt · too hard for it
Decision Index 0.4.1: HLE (accuracy) submitted	14.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 184/246	very hard · avg 13%	▇ 0.0%	blunt

workflows▃▁▁▂▁▂▂▆█▄▁▁ #114 of 114 * · 8.1% of its score · 2 tests

Trails certo-decision-model (DecisionBench 7628c0da), gte-reranker-modernbert-base (DecisionBench f7481e60), KaLM-Reranker-V1-Nano-R2 (DecisionBench 3902d645) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecideBench v1: ticket triage	34.0% ✎	▄·····▂█·▆·▂ beats 0/10	very easy · avg 90%	▇▇▇ 6.5%	sharp
DecideBench v1: returns policy	28.0% ✎	▃··▃··▃·▅▅█▃ beats 0/10	easy · avg 81%	▇ 1.6%	sharp · noisy

other tests2 not in a task · 4.6% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	3.5400 points ✎	▃▂▂▃▃▃▄▅▅▇█▃ beats 5/247	avg 41.206 points	▇ 3.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	6.5800 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 3/247	avg 38.861 points	▇ 1.6%	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/SupersonicLabs ↗

$ how the score was worked out · Decision Index 0.4.1 73%, DecideBench (Cho Yin Yong) 26%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 73%	CC BY 4.0
DecideBench (Cho Yin Yong)	8	▇▇▇▇▇▇▇▇ 26%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 18.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	57.6%	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]	35.0%	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