whatmodel.sh / decision / kev-4b (DecisionBench 485ace87)

kev-4b (DecisionBench 485ace87)

+ contribute

kev-4b (DecisionBench 485ace87) is an open-weights decision model from Jared Palmer. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: jaredpalmer/kev-4b, revision 485ace8703592fcf405488b262449990824cfed1; decision-model; adapter jev-compatible-server-v1; probability source native_probability_distribution. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

· Weights licence ↗

55.3±1.7#157 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of kev-4b (DecisionBench 485ace87), out of 357 with a score, then more from Jared Palmer.

#	model	score	where	RAM	released
157	Amber 4B MLukauskas	55±1	model files
158	StartLux-Decision v1.1 2B StartLux	55±1	model files
159	kev-4b (DecisionBench 485ace87) Jared Palmer	55±2	model files
160	Jebadiah 9B v2.1 (Ollaya Q8_0) frontier-infra	55±3	local	~9.1GB	2026-10
161	Standard One 8B SH (v4) Standard Thinking	55±1	model files
	more from Jared Palmer
88	Kev 27B Jared Palmer	62±1	model files		2026-09
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

workflows▁▁▁▂▁▂▂▆█▄▁▁ #52 of 114 · 99% of its score · 27 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Together Tev1 Qwen3.5-4B, Jebadiah 9B v2.1 (Ollaya Q8_0) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · action selection (all-request accuracy) submitted	54.3% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 30/56	medium · avg 51%	▇▇▇▇▇▇▇▇ 20%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	75.7% ✎	▁▁▁▁▂▂▁▁▁▁▃█ beats 43/56	medium · avg 64%	▇▇▇▇▇ 13%	sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted	73.0% ✎	▁▁·▃▁▁▁▁▁▁▃█ beats 49/56	medium · avg 58%	▇▇▇▇ 11%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	46.0% ✎	▃▂▁▂▂▂▄▁▃▆██ beats 41/56	medium · avg 39%	▇▇▇▇ 9.2%	at its level
DecisionBench v1 · verification (all-request accuracy) submitted	59.5% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 35/56	medium · avg 56%	▇▇▇ 6.3%	blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	49.5% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 38/56	medium · avg 46%	▇▇ 5.1%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	49.3% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 42/56	medium · avg 45%	▇▇ 4.3%	at its level
DecisionBench v1 · triage (all-request accuracy) submitted	86.0% ✎	▁·▁·▂▃▄▃▂█▄▂ beats 42/56	easy · avg 78%	▇▇ 4.3%	sharp

19 more tests

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · completion assessment (all-request accuracy) submitted	91.0% ✎	▁▁▂▃▄·▂▁▁▆█▂ beats 33/56	very easy · avg 86%	▇▇ 4.1%	sharp
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	93.1% ✎	▃▃▂·▁▁▁▁▁▁█▅ beats 31/56	very easy · avg 86%	▇ 3.5%	sharp · noisy
DecisionBench v1 · content classification (all-request accuracy) submitted	79.0% ✎	▁····▁▁▁▁▁▁█ beats 36/56	easy · avg 73%	▇ 3.3%	typical
DecisionBench v1 · review scoring (all-request accuracy) submitted	43.0% ✎	▁······▂▃▅▇█ beats 20/56	medium · avg 52%	▇ 2.9%	at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	56.0% ✎	▁▁·▁▁▂▃▂▃▁▁█ beats 41/56	medium · avg 35%	▇ 2.3%	at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	45.0% ✎	▁▁·▁▁▁▃▁▂▁▁█ beats 41/56	hard · avg 29%	▇ 2.1%	at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted	67.0% ✎	▁▁·▁▂▂▁▃▃█▇▃ beats 41/56	medium · avg 62%	▇ 1.9%	blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted	48.3% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 35/56	medium · avg 52%	▇ 1.2%	at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	50.4% ✎	█▁▂▁▁▁▁▁▂▅▁▁ beats 10/56	easy · avg 74%	▇ 0.7%	noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted	50.0% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 16/56	easy · avg 66%	▇ 0.7%	blunt · at its level
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	38.8% ✎	▁▁▁▂▆▃▃█···▁ beats 18/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted	58.0% ✎	▂·····▆█▂▂▄▇ beats 20/56	easy · avg 77%	▇ 0.4%	noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	37.0% ✎	▂▁·▂▁▁▁▄▁▂▂█ beats 50/56	hard · avg 21%	▇ 0.3%	blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	48.0% ✎	▁·▁▁·▁▁█▂▃█▂ beats 5/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	45.0% ✎	▁····▃▅▃▂▂·█ beats 5/56	easy · avg 82%	▇ 0.2%	noisy
DecisionBench v1 · context management (all-request accuracy) submitted	50.0% ✎	▁·····▁▇▆▁█▃ beats 5/56	easy · avg 73%	▇ 0.2%	blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	93.8% ✎	▁·▁▄▇▄▅▄▂▃▄█ beats 38/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	97.7% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 51/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	80.4% ✎	█▁···▁·▂▆▅▃▂ beats 51/56	medium · avg 42%	▇ 0.0%	blunt · at its level · noisy

$ 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 the revision recorded by the benchmark. 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 · Hanno Labs DecisionBench v1 r… 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
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified	27	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC0 1.0
prior · pull toward the middle		▇ 1%
weighted average		= 55.3

$ 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