whatmodel.sh / decision / baselabs joey-1 (2B)

baselabs joey-1 (2B)

+ contribute

baselabs joey-1 (2B) is an open-weights decision model from baselabs. Its published size is 2.72B parameters. Licence: mit.

Catalogue identity notes

Exact Decision Index tested engine joey-1; reported model baselabs joey-1 (2B). Type: full fine-tune; 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. Native Baseten hosted endpoint verified 2026-10-31; historical hosted and downloaded weight hashes are not assumed identical.

Model information sources

· Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

52.2±1.0#188 of 355 decision modelsfrom 60 benchmark results across 3 sources

$ how it compares

The decision models ranked either side of baselabs joey-1 (2B), out of 357 with a score, then more from baselabs.

#	model	score	where	RAM	released
188	Jebadiah 9B v2 (JevBench mini) Frontier Infra	52±2	source code
189	jiwo 4B v2 eljiwo	52±1	model files		2026-10-09
190	baselabs joey-1 (2B) baselabs	52±1	api price unknown
191	QEV-2B ken-jo	52±4	model files
192	Jebadiah 4B v2 (Ollaya Q8_0) frontier-infra	52±3	local	~5.5GB	2026-10
	more from baselabs
2	baselabs mammoth-1 (27B) baselabs	75±1	model files		2026-10-21
24	baselabs elephant-1 (9B) baselabs	69±1	model files		2026-10-21

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #39 of 250 · 5.0% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, vLLM-SR d3-ultra (Decision 3.0, 27B) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: API-Bank (accuracy) submitted	85.0% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 156/236	easy · avg 70%	▇ 1.5%	sharp · at its level · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.6% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 207/246	very easy · avg 92%	▇ 1.5%	sharp · maxed out · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	90.8% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 228/246	easy · avg 72%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	96.6% ✎	█▁▁▃▄▄▆▄▁▃▁▃ beats 216/243	medium · avg 37%	▇ 0.7%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	66.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 177/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	77.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #111 of 258 · 12% of its score · 13 tests

Beats AutoTrust-JEV-27B v1.1, Quyet-1.0-Large, OneJev1.6-9B here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-0.8b, Jev-Style 2B v4 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: MIRACL pairwise (Arabic)	83.0% ✎	▂···▁··▃▄▂█▇ beats 4/29	easy · avg 84%	▇ 2.6%	at its level
System One Bench: MASSIVE intent (Arabic)	84.5% ✎	▄·▁·▁▃▃▃█▄▇▇ beats 14/29	easy · avg 76%	▇ 2.6%	typical
System One Bench: MIRACL rerank (Arabic)	62.0% ✎	▁▃·▁▁·▂·▄▄█▇ beats 1/29	easy · avg 79%	▇ 1.6%	typical
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	38.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 88/246	medium · avg 38%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.5% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 161/246	medium · avg 47%	▇ 1.4%	at its level
System One Bench: MASSIVE scenario (Arabic)	71.5% ✎	▃▁·▄▃▂█▂▁▁·▃ beats 18/29	medium · avg 60%	▇ 0.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	87.8% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 212/246	easy · avg 74%	▇ 0.4%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	93.8% ✎	█▅▅▄▃▂▃▁▁▁·▁ beats 226/245	easy · avg 70%	▇ 0.3%	at its level · noisy

5 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	95.8% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 217/238	easy · avg 83%	▇ 0.3%	sharp · noisy
System One Bench: AG News (English)	85.0% ✎	▁···▅▁▅▂▆█▂▅ beats 1/29	easy · avg 88%	▇ 0.2%	blunt
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	92.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 222/238	easy · avg 79%	▇ 0.2%	noisy
System One Bench: Banking77 (English)	93.0% ✎	█▅▆█▅▃▃▃···▂ beats 21/26	very easy · avg 87%	▇ 0.0%	blunt · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	65.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #149 of 256 · 22% of its score · 18 tests

Beats Solar Decide, JoshuaSP diffgemma (decision readout), PurpleMIST-Flash-1.0 here, though they rank higher overall. Trails Decider 2B, Crivo-1B, LatentMesh Blitz 2B v1 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	83.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 105/246	very easy · avg 85%	▇▇ 3.8%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	76.0% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 105/246	easy · avg 74%	▇ 3.5%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	63.8% ✎	▁▂▃▅▅█▂····▁ beats 119/246	medium · avg 60%	▇ 3.3%	at its level
System One Bench: OSACT4 offensive (Arabic)	83.0% ✎	▁······▁▃█▇▄ beats 5/29	easy · avg 84%	▇ 1.8%	sharp · at its level
System One Bench: BoolQ (English)	80.0% ✎	▁▁▁▃·▁▃▃▇▇█▅ beats 3/29	easy · avg 86%	▇ 1.7%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	55.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 164/246	medium · avg 44%	▇ 1.4%	at its level
System One Bench: SST-2 (English)	86.0% ✎	▁·▃▁▂▂▃▅█·▂▁ beats 2/29	easy · avg 92%	▇ 1.2%	typical
System One Bench: SST-5 (English)	40.5% ✎	▃·▁▁▃·▇▄▄▄█▅ beats 1/29	medium · avg 51%	▇ 0.8%	blunt · at its level

10 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	86.2% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 241/246	easy · avg 71%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: ACOS (per-review F1) submitted	63.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 237/246	hard · avg 22%	▇ 0.7%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	70.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 141/246	medium · avg 62%	▇ 0.6%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	81.4% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 196/246	easy · avg 66%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	90.5% ✎	▁···▁▁▁▁▃▆█▃ beats 154/246	easy · avg 84%	▇ 0.5%	noisy
System One Bench: XNLI Arabic (Arabic)	64.7% ✎	▄▁▃▃▄▇█▅▃▁·▃ beats 6/29	medium · avg 68%	▇ 0.4%	at its level
System One Bench: XNLI French (French)	74.7% ✎	▂▅·▁▃▅▅█▃▁·▃ beats 7/29	medium · avg 76%	▇ 0.4%	blunt · at its level
System One Bench: Tweet sentiment (Arabic)	66.0% ✎	▁······▁▁▄█▄ beats 12/29	medium · avg 62%	▇ 0.3%	blunt · at its level
System One Bench: XNLI English (English)	84.0% ✎	▃·▁·▃▇█▄█▃▃▁ beats 8/29	easy · avg 85%	▇ 0.1%	blunt · noisy
System One Bench: DAIR Emotion (English)	52.5% ✎	██▃·····▁··▁ beats 0/29	medium · avg 59%	▇ 0.0%	blunt · at its level

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #35 of 247 · 5.8% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), Nace.AI Drex Max v1 (27B) here, though they rank higher overall. Trails Kas 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	60.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 102/246	medium · avg 61%	▇ 2.5%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	63.0% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 173/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	96.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 212/246	easy · avg 83%	▇ 0.8%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	66.1% ✎	▁········▁▇█ beats 206/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	76.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 202/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	61.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 214/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #187 of 263 · 41% of its score · 15 tests

Trails Sieve 2B, FLock this-that 1.2, Decider 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Etsabary · 1342 text decisions	57.6% ✎	▁··▃·▃▅▁▃▂▂█ beats 2/24	medium · avg 47%	▇▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	36.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 75/246	medium · avg 46%	▇▇▇ 6.4%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	57.0% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 69/246	easy · avg 70%	▇▇ 4.7%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	88.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 228/246	easy · avg 66%	▇▇ 4.1%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	79.3% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 70/246	very easy · avg 90%	▇ 3.0%	sharp
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	44.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 128/246	medium · avg 45%	▇ 2.1%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	77.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 116/246	easy · avg 78%	▇ 2.1%	typical
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	30.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 57/246	medium · avg 39%	▇ 1.9%	blunt · at its level

7 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	90.1% ✎	▁▁▂▁▂▂▃▂▃▆█▅ beats 65/246	very easy · avg 96%	▇ 1.6%	sharp · maxed out · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	56.2% ✎	▁▁▁▁▁▁▁▂▅█▂▃ beats 241/246	hard · avg 22%	▇ 0.8%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	83.1% ✎	▁▁▂█▅▄▁▁▃▁▁▁ beats 236/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	75.1% ✎	██▄▃▃▄▁▁···▁ beats 184/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	95.4% ✎	▁███▆▅▃▃▁▁▃▁ beats 240/246	easy · avg 71%	▇ 0.6%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	25.6% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 228/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	16.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 225/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #55 of 79 * · 7.2% of its score · 1 test

Trails Valen-4B, JPT-4B Qwen3.5-4B LoRA, LiquidAI d1-3B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Etsabary · 200 image decisions	47.0% ✎	▃▂··▂▃▂·█▃▂▂ beats 0/14	medium · avg 45%	▇▇▇ 7.2%	sharp · at its level

workflows▁▁▁▂▁▂▂▆█▄▁▁ #72 of 114 * · 2.1% of its score · 1 test

Trails Solar Decide Flash, InternLM Intern-Decision Qwen3.5-4B, StartLux-Decision v1.1 0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: Typed decisions (English)	62.4% ✎	▁▁·▁▁▃▅▄▇██▁ beats 4/29	medium · avg 63%	▇ 2.1%	blunt · at its level

other tests2 not in a task · 5.0% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	49.6900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 143/247	avg 41.206 points	▇ 3.2%	blunt
Decision Index 0.4.1: private new domains (equated points)	15.2500 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 58/247	avg 38.861 points	▇ 1.8%	blunt

$ where to run it

Through an API

api · OpenRouter · price unknown · openrouter.ai ↗

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/baselabs ↗

$ how the score was worked out · Decision Index 0.4.1 64%, Etsabary · decision benchmarks 19%, System One Bench (Ali Alhashi… 17%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%	CC BY 4.0
Etsabary · decision benchmarks	2	▇▇▇▇▇▇ 19%	MIT
System One Bench (Ali Alhashimi)	16	▇▇▇▇▇ 17%	CC-BY-4.0
prior · pull toward the middle		▇ 0%
weighted average		= 52.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	77.8%	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]	65.0%	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