whatmodel.sh / decision / Nace.AI Drex Max v1 (27B)

Nace.AI Drex Max v1 (27B)

+ contribute

Nace.AI Drex Max v1 (27B) is an open-weights decision model from Nace-Deepinfra. Its published size is 26.09B parameters.

Catalogue identity notes

Exact Decision Index tested engine drex-max-v1; reported model Nace.AI Drex Max v1 (27B). Type: full fine-tune; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark.

Model information sources

· Parameter count ↗

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

70.2±1.2#14 of 355 decision modelsfrom 71 benchmark results across 4 sources

$ how it compares

The decision models ranked either side of Nace.AI Drex Max v1 (27B), out of 357 with a score.

#	model	score	where	released
12	KnowLine 35B-A3B Gen1.5 PelaAI	71±2	model files	2026-10-22
13	H2O Lightning 31B v1.1 H2O.ai	70±2	request access
14	Nace.AI Drex Max v1 (27B) Nace-Deepinfra	70±1	model files
15	Bespoke Nimble v4 Max (27B) Bespoke Labs	70±1	model files	2026-10
16	Turion Jev 31B Turion.AI	70±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #17 of 250 · 3.3% of its score · 6 tests

Beats Jeffan-31b-1710, Sieve 31B v3, Fastino GLiDE 1.2 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: API-Bank (accuracy) submitted	88.4% ✎	▁▁▁▁▁▁▁▂▃▂█▃ beats 222/236	easy · avg 70%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	69.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 232/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	86.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 182/246	easy · avg 72%	▇ 0.6%	noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	72.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 179/243	medium · avg 37%	▇ 0.6%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.9% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 227/246	very easy · avg 92%	▇ 0.5%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.7% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #11 of 258 · 12% of its score · 13 tests

Beats Fastino GLiDE 1.2, KnowLine 31B Gen1, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails OneShot 27B, StartLux-Decision v1.1 9B, baselabs elephant-1 (9B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: MIRACL pairwise (Arabic)	89.5% ✎	▂···▁··▃▄▂█▇ beats 17/29	easy · avg 84%	▇ 2.4%	typical
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	49.9% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 230/246	medium · avg 38%	▇ 2.2%	blunt · at its level
System One Bench: MASSIVE intent (Arabic)	88.0% ✎	▄·▁·▁▃▃▃█▄▇▇ beats 21/29	easy · avg 76%	▇ 2.0%	typical
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	62.7% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 238/246	medium · avg 47%	▇ 1.8%	at its level
System One Bench: MIRACL rerank (Arabic)	89.5% ✎	▁▂·▁▁·▂·▄▄█▇ beats 27/29	easy · avg 79%	▇ 1.4%	typical
System One Bench: MASSIVE scenario (Arabic)	73.0% ✎	▃▁·▄▃▂█▂▁▁·▃ beats 22/29	medium · avg 60%	▇ 1.0%	typical
Decision Index 0.4.1: HoVer (accuracy) submitted	87.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 214/246	easy · avg 74%	▇ 0.4%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	75.2% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 153/245	easy · avg 70%	▇ 0.4%	noisy

5 more tests

test	result	vs the others in its run	difficulty	counts	why
System One Bench: AG News (English)	90.5% ✎	▁···▅▁▅▂▆█▂▅ beats 22/29	easy · avg 88%	▇ 0.3%	blunt
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 188/238	easy · avg 79%	▇ 0.2%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	95.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 213/238	easy · avg 83%	▇ 0.2%	sharp · maxed out · noisy
System One Bench: Banking77 (English)	90.5% ✎	█▅▆█▅▃▃▃···▂ beats 18/26	very easy · avg 87%	▇ 0.0%	blunt · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	57.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #8 of 256 · 20% of its score · 18 tests

Beats Jeffan-31b-1710, Sieve 31B v3, Fastino GLiDE 1.2 here, though they rank higher overall. Trails Clef-omni, vLLM-SR d3 (27B), AutoTrust-JEV-27B v1.1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	77.1% ✎	▁▂▃▅▅█▂····▁ beats 216/246	medium · avg 60%	▇ 3.4%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	86.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 232/246	easy · avg 74%	▇ 3.2%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	73.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 243/246	medium · avg 44%	▇ 1.8%	at its level
System One Bench: BoolQ (English)	93.0% ✎	▁▁▁▃·▁▃▃▇▇█▅ beats 29/29	easy · avg 86%	▇ 1.7%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	97.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 237/246	very easy · avg 85%	▇ 1.5%	sharp · maxed out
System One Bench: OSACT4 offensive (Arabic)	93.5% ✎	▁······▁▃█▇▄ beats 24/29	easy · avg 84%	▇ 1.3%	sharp
Decision Index 0.4.1: ACOS (per-review F1) submitted	41.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 204/246	hard · avg 22%	▇ 1.3%	at its level · noisy
System One Bench: SST-5 (English)	59.0% ✎	▃·▁▁▃·▇▄▄▄█▅ beats 22/29	medium · avg 51%	▇ 1.2%	blunt · at its level

10 more tests

test	result	vs the others in its run	difficulty	counts	why
System One Bench: SST-2 (English)	96.0% ✎	▁·▃▁▂▂▃▅█·▂▁ beats 26/29	easy · avg 92%	▇ 1.0%	maxed out
Decision Index 0.4.1: VAST (macro-F1) submitted	78.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 201/246	medium · avg 62%	▇ 0.7%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	83.9% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 205/246	easy · avg 71%	▇ 0.6%	noisy
System One Bench: XNLI Arabic (Arabic)	89.3% ✎	▄▁▃▁▄▇█▅▃▁·▃ beats 28/29	medium · avg 68%	▇ 0.5%	at its level
System One Bench: XNLI French (French)	91.3% ✎	▂▅·▁▁▅▅█▃▁·▃ beats 29/29	medium · avg 76%	▇ 0.5%	blunt
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	84.8% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 232/246	easy · avg 66%	▇ 0.4%	noisy
System One Bench: Tweet sentiment (Arabic)	69.0% ✎	▁······▁▁▄█▄ beats 17/29	medium · avg 62%	▇ 0.4%	blunt · at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	94.6% ✎	▁···▁▁▁▁▃▆█▃ beats 228/246	easy · avg 84%	▇ 0.3%	maxed out · noisy
System One Bench: XNLI English (English)	95.3% ✎	▃·▁·▃▇█▄█▃▃▃ beats 29/29	easy · avg 85%	▇ 0.1%	blunt · noisy
System One Bench: DAIR Emotion (English)	65.0% ✎	██▃·····▁··▁ beats 27/29	medium · avg 59%	▇ 0.0%	blunt · at its level

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #50 of 247 · 6.6% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B) here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Clef-flash 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	80.5% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 225/246	medium · avg 61%	▇ 2.5%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	64.5% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 198/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	66.2% ✎	▁········▁▇█ beats 211/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	63.0% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 185/237	hard · avg 21%	▇ 0.9%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 198/246	easy · avg 83%	▇ 0.5%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	50.8% ✎	▁▂▄█▇▅▃▁▄▄▁▁ beats 179/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #18 of 263 · 37% of its score · 15 tests

Beats StartLux-Decision v1.1 27B, KnowLine 35B-A3B Gen1.5 here, though they rank higher overall. Trails d1 (hosted), Jev 1.13, Matilda Decision v1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Etsabary · 1342 text decisions	84.0% ✎	▁··▂·▃▅▁▃▂▂█ beats 23/24	medium · avg 47%	▇▇▇▇ 10%	sharp
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	72.8% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 223/246	medium · avg 46%	▇▇▇ 7.0%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	93.7% ✎	▄▆▄▄█▇▇▄▃▁▃▁ beats 244/246	easy · avg 66%	▇ 3.5%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	87.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 220/246	easy · avg 70%	▇ 3.4%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	56.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 238/246	medium · avg 39%	▇ 2.8%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	83.4% ✎	▁··▄█▆▆▆▅▅▃▁ beats 227/246	medium · avg 45%	▇ 2.3%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	95.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 235/246	easy · avg 78%	▇ 1.6%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	31.3% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 160/246	hard · avg 22%	▇ 1.5%	at its level

7 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	69.7% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 212/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 212/246	very easy · avg 90%	▇ 0.9%	sharp · maxed out
Decision Index 0.4.1: CRUXEval (accuracy) submitted	86.8% ✎	██▄▃▃▄▁▁···▁ beats 229/246	medium · avg 58%	▇ 0.7%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	24.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 216/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	85.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 204/246	easy · avg 71%	▇ 0.6%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 226/246	very easy · avg 96%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	20.0% ✎	▁▁▂▃▆█▇▅▅▃▁▃ beats 245/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #23 of 79 · 11% of its score · 12 tests

Trails Clef-flash, Perplexity Decider Flash v1.2 (4B), Mercury Decide (free endpoint) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	83.5600 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 47/61	avg 63.423 points	▇ 1.4%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	47.2300 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 58/61	avg 22.797 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	85.0000 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 49/61	avg 66.987 points	▇ 1.2%	blunt
Decision Index Vision 0.4: private same skills (points)	68.4100 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 55/61	avg 48.067 points	▇ 1.2%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	40.3100 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 37/61	avg 28.443 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	72.8100 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 52/61	avg 53.651 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	81.2000 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 56/61	avg 62.137 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	97.8100 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 53/61	avg 83.859 points	▇ 0.7%	blunt

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	40.4400 points ✎	▂▄▇▆█▄▄▇▃··▁ beats 59/61	avg 19.676 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	59.7300 points ✎	▁···▁▂▂▂█▄▂▃ beats 44/61	avg 44.994 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	77.3300 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 49/61	avg 67.662 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	92.5900 points ✎	▁··▁▁▁▁▁▂▄█▁ beats 48/61	avg 85.184 points	▇ 0.4%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #25 of 114 * · 2.4% of its score · 1 test

Trails imajev-4b (DecisionBench c9e5f132), reflex-qwen3.5-4b-lora (DecisionBench 9df1cbbb), litjev (DecisionBench 1d4bf0f2) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: Typed decisions (English)	73.0% ✎	▁▁·▁▁▁▅▄▇██▁ beats 22/29	medium · avg 63%	▇ 2.4%	blunt

other tests2 not in a task · 7.3% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	62.7600 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 231/247	avg 41.206 points	▇▇ 4.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	72.3600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 221/247	avg 38.861 points	▇ 2.6%	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/nace-ai ↗

$ how the score was worked out · Decision Index 0.4.1 62%, System One Bench (Ali Alhashi… 16%, Decision Index Vision 0.4 11% and 1 more

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%	CC BY 4.0
System One Bench (Ali Alhashimi)	16	▇▇▇▇▇ 16%	CC-BY-4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇ 11%	CC BY 4.0
Etsabary · decision benchmarks	1	▇▇▇ 10%	MIT
prior · pull toward the middle		▇ 1%
weighted average		= 70.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.7%	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]	57.6%	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