Kev 27B

+ contribute

Kev 27B is an open-weights decision model from Jared Palmer, released September 2026. Its published size is 27.8B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine kev-27b; reported model Kev 27B. 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.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

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

61.9±1.3#88 of 355 decision modelsfrom 44 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Kev 27B, out of 357 with a score, then more from Jared Palmer.

#	model	score	where	RAM	released
86	Tern-35B-A3B matthewagi	62±1	model files
87	garum (Gemma 4 31B) plantwaterer	62±1	model files
88	Kev 27B Jared Palmer	62±1	model files		2026-09
89	Shisa DE-2.1 (repeat) Shisa.AI	62±1	model files
90	Perplexity Decider Flash v1.2 (4B) Perplexity	62±1	local	~10GB
	more from Jared Palmer
159	kev-4b (DecisionBench 485ace87) Jared Palmer	55±2	model files
162	kev-8b (DecisionBench c80773da) Jared Palmer	55±2	model files
209	Kev 9B v2 Jared Palmer	50±1	model files		2026-09-30

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #35 of 250 · 6.3% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, Ainvest-Decision-27B v1.0 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	83.1% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 134/236	easy · avg 70%	▇ 1.9%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 222/246	very easy · avg 92%	▇ 1.2%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	63.6% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 156/243	medium · avg 37%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	68.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 207/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	62.1% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 72/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #71 of 258 · 7.0% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, oenogarum (Gemma 4 31B), Decider 31B (NVFP4) here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B 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) submitted	48.5% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 207/246	medium · avg 38%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	57.4% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 185/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	69.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 98/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	62.4% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 96/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	86.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 88/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	86.1% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 145/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	23.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #69 of 256 · 21% of its score · 9 tests

Beats Turion Jev 31B, AJev lm6q (Gemma 4 31B), oenogarum (Gemma 4 31B) here, though they rank higher overall. Trails Sieve 4B, Decider 35B-A3B, Sieve 9B v2 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	70.9% ✎	▁▂▃▅▅█▂····▁ beats 166/246	medium · avg 60%	▇▇ 5.3%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	83.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 189/246	easy · avg 74%	▇▇ 5.1%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	94.4% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 183/246	very easy · avg 85%	▇ 3.6%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	61.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 192/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	23.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 132/246	hard · avg 22%	▇ 1.5%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	68.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 128/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	77.8% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 140/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 184/246	easy · avg 66%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	94.0% ✎	▁···▁▁▁▁▃▆█▃ beats 213/246	easy · avg 84%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #56 of 247 · 10% of its score · 6 tests

Beats OneJev1.6-27B, mogan-decision-31B-it, Cerno 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	70.3% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 154/246	medium · avg 61%	▇▇ 3.9%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 160/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.5% ✎	▁········▁▇█ beats 156/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	35.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 154/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 194/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.5% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 74/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #70 of 263 · 42% of its score · 14 tests

Beats StartLux-Decision v1.1 9B, Sieve 27B v2, RSI-Jev v6.1 VL 27B (effort auto) here, though they rank higher overall. Trails Solar Decide, 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: MMLU-Pro (accuracy) submitted	67.3% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 192/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	84.0% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 179/246	easy · avg 70%	▇▇ 6.2%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	79.9% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 192/246	easy · avg 66%	▇▇ 5.9%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	71.3% ✎	▁··▄█▆▆▆▅▅▃▁ beats 191/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	47.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 172/246	medium · avg 39%	▇ 3.6%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	88.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 187/246	easy · avg 78%	▇ 2.8%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.8% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 187/246	very easy · avg 90%	▇ 2.4%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	27.8% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 124/246	hard · avg 22%	▇ 1.8%	at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	64.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 172/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	77.2% ✎	██▄▃▃▄▁▁···▁ beats 188/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 192/246	very easy · avg 96%	▇ 1.1%	sharp · maxed out · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	74.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 151/246	easy · avg 71%	▇ 0.9%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	18.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 155/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 92/246	very hard · avg 13%	▇ 0.0%	blunt

other tests4 not in a task · 13% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	55.1000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 169/247	avg 41.206 points	▇▇ 6.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	66.2600 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 204/247	avg 38.861 points	▇ 3.3%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	64.1607 points ✎	▃···▃·▃▃█▅▅█ beats 9/13	avg 32.166 points	▇ 2.6%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	93.7172 points ✎	▂······▂▆▂██ beats 13/13	avg 70.133 points	▇ 0.7%	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/jaredpalmer ↗

$ how the score was worked out · Decision Index 0.4.1 96%, Benchmark Heaven (own decisio… 3%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%	CC BY 4.0
Benchmark Heaven (own decision evaluations)	2	▇ 3%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 61.9

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.8%	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]	23.8%	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