whatmodel.sh / decision / djev-dev (DecisionBench f7f5b7f5)

djev-dev (DecisionBench f7f5b7f5)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

djev-dev (DecisionBench f7f5b7f5) is an open-weights decision model from Davipar. Its published size is 25.823778864B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: Davipar/djev-dev, revision f7f5b7f5fa82ffc52addd066915886d497f5517b; language-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 ↗ · Parameter count ↗

Published served parameter count; not a RAM or download-size measurement.

55.7±1.7#149 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of djev-dev (DecisionBench f7f5b7f5), out of 357 with a score, then more from Davipar.

#modelscorewhereRAMreleased
149decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout) aminry56±1source code2026-10-04
150Jegue 0.1 (9B) fdemelo56±1model files
151djev-dev (DecisionBench f7f5b7f5) Davipar56±2model files
152open-alternative-jev (DecisionBench 4a85df18) IkerMoel56±2source code
153Open-Jev-9B (DecisionBench 47e96688) ZefanCai56±2model files2026-09-20
more from Davipar
210djev diffgemma (decision readout) Davipar50±1source code

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #49 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.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted56.0% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 32/56medium · avg 51%▇▇▇▇▇▇▇▇ 20%at its level
DecisionBench v1 · routing (all-request accuracy) submitted70.3% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 31/56medium · avg 64%▇▇▇▇▇ 13%sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted70.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 36/56medium · avg 58%▇▇▇▇ 11%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted48.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 49/56medium · avg 39%▇▇▇▇ 9.2%at its level
DecisionBench v1 · verification (all-request accuracy) submitted60.0% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 39/56medium · avg 56%▇▇▇ 6.3%blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted46.2% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 33/56medium · avg 46%▇▇ 5.2%at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted49.9% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 43/56medium · avg 45%▇▇ 4.4%at its level
DecisionBench v1 · triage (all-request accuracy) submitted84.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 36/56easy · avg 78%▇▇ 4.3%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · completion assessment (all-request accuracy) submitted92.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 41/56very easy · avg 86%▇▇ 4.0%sharp
DecisionBench v1 · bounded extraction (all-request accuracy) submitted94.0% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 40/56very easy · avg 86%▇ 3.4%sharp · noisy
DecisionBench v1 · content classification (all-request accuracy) submitted78.0% ✎▁····▁▁▁▁▁▁█ beats 32/56easy · avg 73%▇ 3.3%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted48.0% ✎▁······▂▃▅▇█ beats 25/56medium · avg 52%▇ 2.9%at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted57.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 44/56medium · avg 35%▇ 2.3%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted47.0% ✎▁▁·▁▁▁▃▁▂▁▁█ beats 47/56hard · avg 29%▇ 2.2%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted62.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 28/56medium · avg 62%▇ 1.9%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted48.1% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 34/56medium · avg 52%▇ 1.2%at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted49.4% ✎█▄▃▁▁▃▂▂▁·▁▁ beats 10/56easy · avg 66%▇ 0.7%blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted67.7% ✎█▁▂▃▁▁▁▁▂▅▁▁ beats 29/56easy · avg 74%▇ 0.7%noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted49.9% ✎▁▁▁▂▆▃▃█···▁ beats 28/56medium · avg 52%▇ 0.5%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted96.0% ✎▂·····▆█▂▂▄▇ beats 48/56easy · avg 77%▇ 0.4%noisy
DecisionBench v1 · document classification (all-request accuracy) submitted32.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 40/56hard · avg 21%▇ 0.3%blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted67.0% ✎▁·▁▁·▁▁█▃▃█▂ beats 25/56easy · avg 71%▇ 0.3%blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted81.0% ✎▁····▃▅▃▂▂·█ beats 27/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted54.5% ✎▁·····▁▇▆▁█▃ beats 14/56easy · avg 73%▇ 0.2%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted98.0% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 42/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted96.3% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 44/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted77.9% ✎█▁···▁·▂▆▅▃▂ beats 49/56medium · avg 42%▇ 0.0%blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. 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/google ↗

$ 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

sourceresultsshare of the scorelicence
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified27CC0 1.0
prior · pull toward the middle
weighted average= 55.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit 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 · sources and licences · json