whatmodel.sh / decision / openjev-sglang (DecisionBench 1355db6a)

openjev-sglang (DecisionBench 1355db6a)

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

openjev-sglang (DecisionBench 1355db6a) is an open-weights decision model from ekzhang. Its published size is 35.951822704B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: ekzhang/openjev-sglang, revision 1355db6a052410cfd62085d94b58866fd0f2c3c5; language-model; adapter jev-compatible-server-native-systemone-grouped-v1; probability source native-with-anchored-wide-choice-reconstruction. 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.

59.7±1.7#111 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of openjev-sglang (DecisionBench 1355db6a), out of 357 with a score.

#modelscorewhereRAMreleased
110decider-35b-a3b (DecisionBench d9783c58) Mapika60±2model files2026-09-20
111Cerno 9B v1.1 apertixai60±1model files2026-10-19
112openjev-sglang (DecisionBench 1355db6a) ekzhang60±2model files
113JEV-27B AutoTrust AI Lab60±1model files
114simple-jev · Qwen3.8-27B (featherless) (decision readout) featherless-ai60±1source code

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #29 of 114 · 99% of its score · 27 tests

Beats d1.1 (hosted), Span-02 (Gemma 4 26B-A4B), Mercury Decide (free endpoint) here, though they rank higher overall. Trails StartLux-Decision v1.1 2B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted60.9% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 44/56medium · avg 51%▇▇▇▇▇▇▇▇ 21%at its level
DecisionBench v1 · routing (all-request accuracy) submitted75.7% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 44/56medium · avg 64%▇▇▇▇▇ 13%sharp
DecisionBench v1 · navigation (all-request accuracy) submitted72.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 46/56medium · avg 58%▇▇▇▇ 10%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted43.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 34/56medium · avg 39%▇▇▇▇ 10%at its level
DecisionBench v1 · verification (all-request accuracy) submitted60.0% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 37/56medium · avg 56%▇▇▇ 6.6%blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted53.5% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 40/56medium · avg 46%▇▇ 5.5%at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted49.1% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 41/56medium · avg 45%▇▇ 4.7%at its level
DecisionBench v1 · triage (all-request accuracy) submitted87.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 47/56easy · avg 78%▇▇ 3.8%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · completion assessment (all-request accuracy) submitted96.0% ✎▁▁▂▃▄·▂▁▁▆█▃ beats 55/56very easy · avg 86%▇ 3.3%sharp · maxed out
DecisionBench v1 · content classification (all-request accuracy) submitted80.0% ✎▁····▁▁▁▁▁▁█ beats 46/56easy · avg 73%▇ 3.0%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted62.0% ✎▁······▂▃▅▇█ beats 50/56medium · avg 52%▇ 3.0%at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted94.6% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 45/56very easy · avg 86%▇ 2.6%sharp · maxed out · noisy
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted56.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 42/56medium · avg 35%▇ 2.5%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted47.0% ✎▁▁·▁▁▁▃▁▂▁▁█ beats 46/56hard · avg 29%▇ 2.4%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted68.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 45/56medium · avg 62%▇ 2.0%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted60.6% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 43/56medium · avg 52%▇ 1.3%at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted75.4% ✎█▄▃▁▁▃▂▂▁·▁▁ beats 42/56easy · avg 66%▇ 0.8%blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted87.6% ✎█▁▂▁▁▁▁▁▂▅▁▁ beats 45/56easy · avg 74%▇ 0.7%noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted63.3% ✎▁▁▁▂▆▃▃█···▁ beats 51/56medium · avg 52%▇ 0.6%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted98.0% ✎▂·····▆█▂▂▄▇ beats 55/56easy · avg 77%▇ 0.4%noisy
DecisionBench v1 · document classification (all-request accuracy) submitted37.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 51/56hard · avg 21%▇ 0.4%blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted86.0% ✎▁·▁▁·▁▁█▂▃█▂ beats 49/56easy · avg 71%▇ 0.3%blunt · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted100.0% ✎▁····▃▅▃▂▂·█ beats 51/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted86.5% ✎▁·····▁▇▆▁█▃ beats 34/56easy · avg 73%▇ 0.2%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted98.6% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 44/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted93.8% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 39/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted71.5% ✎█▁···▁·▂▆▅▂▂ beats 44/56medium · 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/nvidia ↗

$ 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= 59.7

$ 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