whatmodel.sh / decision / zerank-2-reranker (DecisionBench 5eae30d5)

zerank-2-reranker (DecisionBench 5eae30d5)

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

zerank-2-reranker (DecisionBench 5eae30d5) is an open-weights decision model from zeroentropy. Its published size is 4.022468096B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: zeroentropy/zerank-2-reranker, revision 5eae30d5ee3c6b2df2ef6d723bde45172d761c4c; classifier; 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.

48.7±1.6#216 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of zerank-2-reranker (DecisionBench 5eae30d5), out of 357 with a score.

#modelscorewhereRAMreleased
216vLLM-SR d3-nano (2B) vLLM Semantic Router49±1local~8.2GB
217Aurelis-2B Leptos Labs49±1model files
218zerank-2-reranker (DecisionBench 5eae30d5) zeroentropy49±2model files
219Kev 4B r10 Jared Palmer49±1local~11GB2026-09-24
220StartLux-Decision v1.1 0.8B StartLux49±1model files

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

$ what it's good at

workflows▁▁▁▂▁▂▃▆█▄▁▁ #76 of 114 · 99% of its score · 27 tests

Trails Solar Decide Flash, InternLM Intern-Decision Qwen3.5-4B, StartLux-Decision v1.1 0.8B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted51.7% ✎▂▁▂▃▄▃▁▁▃█▇▄ beats 28/56medium · avg 51%▇▇▇▇▇▇▇▇ 19%at its level
DecisionBench v1 · routing (all-request accuracy) submitted61.7% ✎▁▁▁▁▂▂▁▁▁▃▃█ beats 25/56medium · avg 64%▇▇▇▇▇▇ 14%sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted55.0% ✎▁▁·▃▁▁▁▁▁▃▃█ beats 24/56medium · avg 58%▇▇▇▇ 11%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted42.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 29/56medium · avg 39%▇▇▇ 8.1%at its level
DecisionBench v1 · verification (all-request accuracy) submitted52.5% ✎▁▁▅▁▃▂▂▃▁▇▇█ beats 23/56medium · avg 56%▇▇ 5.9%blunt · at its level
DecisionBench v1 · completion assessment (all-request accuracy) submitted93.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 42/56very easy · avg 86%▇▇ 5.5%sharp
DecisionBench v1 · bounded extraction (all-request accuracy) submitted61.9% ✎▃▃▂·▁▃▁▁▁▁█▅ beats 20/56very easy · avg 86%▇▇ 5.2%sharp · noisy
DecisionBench v1 · triage (all-request accuracy) submitted80.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 29/56easy · avg 78%▇▇ 5.0%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · document record classification (all-request accuracy) submitted45.7% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 31/56medium · avg 46%▇▇ 4.7%at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted35.9% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 22/56medium · avg 45%▇▇ 3.9%at its level
DecisionBench v1 · content classification (all-request accuracy) submitted70.0% ✎▁····▁▁▁▁▁▃█ beats 22/56easy · avg 73%▇ 3.6%at its level
DecisionBench v1 · review scoring (all-request accuracy) submitted50.0% ✎▁······▂▃▅▇█ beats 27/56medium · avg 52%▇ 2.7%at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted24.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 27/56medium · avg 35%▇ 1.9%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted68.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 44/56medium · avg 62%▇ 1.8%blunt · at its level
DecisionBench v1 · target selection (all-request accuracy) submitted25.0% ✎▁▁·▁▁▁▃▁▂▃▁█ beats 29/56hard · avg 29%▇ 1.7%at its level · noisy
DecisionBench v1 · reasoning (all-request accuracy) submitted44.8% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 29/56medium · avg 52%▇ 1.1%at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted84.2% ✎█▁▂▁▁▁▁▁▃▅▁▁ beats 35/56easy · avg 74%▇ 0.8%at its level · noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted66.1% ✎█▄▃▃▁▃▂▂▁·▁▁ beats 35/56easy · avg 66%▇ 0.7%blunt · at its level
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted31.8% ✎▁▁▁▃▆▃▃█···▁ beats 7/56medium · avg 52%▇ 0.5%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted93.0% ✎▂·····▆█▂▂▄▇ beats 37/56easy · avg 77%▇ 0.5%noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted82.0% ✎▁·▁▁·▁▁█▂▃█▂ beats 36/56easy · avg 71%▇ 0.3%blunt · at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted33.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 41/56hard · avg 21%▇ 0.3%blunt · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted82.0% ✎▁····▃▅▃▂▂·█ beats 28/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted55.5% ✎▁·····▁▇▆▁█▃ beats 16/56easy · avg 73%▇ 0.2%blunt · at its level · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted100.0% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 46/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted98.2% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 53/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted73.8% ✎█▁···▁·▂▆▅▂▂ beats 46/56medium · 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/zeroentropy ↗

$ 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= 48.7

$ 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