whatmodel.sh / decision / Open-Jev-9B (DecisionBench 47e96688)

Open-Jev-9B (DecisionBench 47e96688)

+ contribute

Open-Jev-9B (DecisionBench 47e96688) is an open-weights decision model from ZefanCai, released 20 September 2026. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: ZefanCai/Open-Jev-9B, revision 47e966881e489511c0c7f5633a9e1960a676a551; decision-model; adapter jev-compatible-server-v1-tail4096; probability source calibrated_scalar_head_option_softmax. 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

Release date ↗ · Weights licence ↗

55.7±1.7#151 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Open-Jev-9B (DecisionBench 47e96688), out of 357 with a score, then more from ZefanCai.

#	model	score	where	released
151	djev-dev (DecisionBench f7f5b7f5) Davipar	56±2	model files
152	open-alternative-jev (DecisionBench 4a85df18) IkerMoel	56±2	source code
153	Open-Jev-9B (DecisionBench 47e96688) ZefanCai	56±2	model files	2026-09-20
154	Tev1-4B-experimental (DecisionBench 0b7becf0) Together	56±2	model files
155	muria (Gemma 4 12B) plantwaterer	55±1	model files
	more from ZefanCai
226	Open-Jev-2B (DecisionBench 0c7aa498) ZefanCai	48±2	model files	2026-09-20

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #47 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, Jebadiah 9B v2.1 (Ollaya Q8_0), StartLux-Decision v1.1 2B 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	54.1% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 29/56	medium · avg 51%	▇▇▇▇▇▇▇▇ 20%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	72.0% ✎	▁▁▁▁▂▂▁▁▁▁▃█ beats 34/56	medium · avg 64%	▇▇▇▇▇ 13%	sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted	71.0% ✎	▁▁·▃▁▁▁▁▁▁▃█ beats 40/56	medium · avg 58%	▇▇▇▇ 11%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	42.0% ✎	▃▂▁▂▂▂▄▁▃▆██ beats 31/56	medium · avg 39%	▇▇▇▇ 9.2%	at its level
DecisionBench v1 · verification (all-request accuracy) submitted	63.5% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 52/56	medium · avg 56%	▇▇▇ 6.3%	blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	46.8% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 36/56	medium · avg 46%	▇▇ 5.2%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	48.4% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 38/56	medium · avg 45%	▇▇ 4.4%	at its level
DecisionBench v1 · triage (all-request accuracy) submitted	78.0% ✎	▁·▁·▂▃▄▃▃█▄▂ beats 26/56	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 34/56	very easy · avg 86%	▇▇ 4.0%	sharp
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	94.9% ✎	▃▃▂·▁▁▁▁▁▁█▅ beats 47/56	very easy · avg 86%	▇ 3.4%	sharp · noisy
DecisionBench v1 · content classification (all-request accuracy) submitted	77.0% ✎	▁····▁▁▁▁▁▁█ beats 27/56	easy · avg 73%	▇ 3.2%	typical
DecisionBench v1 · review scoring (all-request accuracy) submitted	56.0% ✎	▁······▂▃▅▇█ beats 35/56	medium · avg 52%	▇ 2.9%	at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	60.0% ✎	▁▁·▁▁▂▃▂▃▁▁█ beats 52/56	medium · avg 35%	▇ 2.3%	at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	48.0% ✎	▁▁·▁▁▁▃▁▂▁▁█ beats 51/56	hard · avg 29%	▇ 2.2%	at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted	70.0% ✎	▁▁·▁▂▂▁▃▃█▇▃ beats 50/56	medium · avg 62%	▇ 1.9%	blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted	57.6% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 40/56	medium · avg 52%	▇ 1.2%	at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted	54.3% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 26/56	easy · avg 66%	▇ 0.8%	blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	69.8% ✎	█▁▂▁▃▁▁▁▂▅▁▁ beats 30/56	easy · avg 74%	▇ 0.7%	noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	38.6% ✎	▁▁▁▂▆▃▃█···▁ beats 15/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted	86.0% ✎	▂·····▆█▂▃▄▇ beats 33/56	easy · avg 77%	▇ 0.4%	noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	34.0% ✎	▂▁·▂▁▁▁▄▁▂▂█ beats 46/56	hard · avg 21%	▇ 0.3%	blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	77.0% ✎	▁·▁▁·▁▁█▂▃█▂ beats 29/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	86.0% ✎	▁····▃▅▃▃▂·█ beats 29/56	easy · avg 82%	▇ 0.2%	noisy
DecisionBench v1 · context management (all-request accuracy) submitted	72.0% ✎	▁·····▁▇▆▁█▃ beats 28/56	easy · avg 73%	▇ 0.2%	blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	100.0% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 50/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	96.8% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 46/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	72.8% ✎	█▁···▁·▂▆▅▂▂ beats 45/56	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/ZefanCai ↗

$ 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		= 55.7

$ 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