whatmodel.sh / decision / gliner2.5-multi-v1 (DecisionBench a221b77a)

gliner2.5-multi-v1 (DecisionBench a221b77a)

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

gliner2.5-multi-v1 (DecisionBench a221b77a) is an open-weights decision model from Fastino. Its published size is 0.287355159B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: fastino/gliner2.5-multi-v1, revision a221b77a8baf4a613b8f8652661d41fa10a5641e; 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.

20.4±1.7#343 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of gliner2.5-multi-v1 (DecisionBench a221b77a), out of 357 with a score, then more from Fastino.

#modelscorewhereRAMreleased
343CLM-v0.1-8B Qwen3-8B heads Contrastive-LM20±1local~15GB
344gliner2.5-base-v1 (DecisionBench 1a8bc24e) Fastino20±2model files
345gliner2.5-multi-v1 (DecisionBench a221b77a) Fastino20±2model files
346NanoJev (DecisionBench 4a19595e) C-Tianyu19±2model files
347Bekko System One v0 17M hotchpotch19±1model files
more from Fastino
4Fastino GLiDE 1.2 Fastino73±1model files2026-10-22
313GLiNER2.5-Decide (DecisionBench 0872ab14) Fastino30±2model files
326gliner2-large-v1 (DecisionBench f32ea6ef) Fastino26±2model files

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

$ what it's good at

workflows▁▁▃▂▁▂▂▆█▄▁▁ #106 of 114 · 99% of its score · 27 tests

Beats CLM-v0.1-8B Qwen3-8B heads here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted21.3% ✎▂▁▃▃▄▃▁▁▂█▇▄ beats 5/56medium · avg 51%▇▇▇▇▇▇ 15%typical
DecisionBench v1 · routing (all-request accuracy) submitted25.7% ✎▁▁▁▁▃▂▁▁▁▁▃█ beats 9/56medium · avg 64%▇▇▇▇▇ 12%sharp
DecisionBench v1 · completion assessment (all-request accuracy) submitted41.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 8/56very easy · avg 86%▇▇▇▇▇ 12%sharp · at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted20.7% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 3/56very easy · avg 86%▇▇▇ 8.7%sharp · at its level · noisy
DecisionBench v1 · triage (all-request accuracy) submitted36.0% ✎▁·▁·▃▃▄▃▂█▄▂ beats 5/56easy · avg 78%▇▇▇ 7.6%sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted17.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 10/56medium · avg 58%▇▇▇ 7.1%sharp
DecisionBench v1 · verification (all-request accuracy) submitted37.0% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 9/56medium · avg 56%▇▇▇ 6.4%blunt · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted19.0% ✎▃▂▁▃▂▂▄▁▃▆██ beats 9/56medium · avg 39%▇▇ 5.9%typical
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · content classification (all-request accuracy) submitted35.0% ✎▁····▁▁▁▃▁▁█ beats 8/56easy · avg 73%▇▇ 4.5%at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted30.0% ✎▂▂·▁▃▄▃▆▄█▁▁ beats 11/56medium · avg 46%▇▇ 4.0%typical
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted25.5% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 7/56medium · avg 45%▇ 3.3%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted0.0% ✎▃······▂▃▅▇█ beats 0/56medium · avg 52%▇ 2.5%at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted41.0% ✎▁▁·▁▂▃▁▃▃█▇▃ beats 7/56medium · avg 62%▇ 2.2%blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted52.7% ✎█▁▂▁▁▁▁▁▂▅▁▁ beats 20/56easy · avg 74%▇ 1.1%at its level · noisy
DecisionBench v1 · reasoning (all-request accuracy) submitted43.0% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 26/56medium · avg 52%▇ 1.1%at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted48.3% ✎█▄▃▁▁▃▂▂▁·▁▁ beats 6/56easy · avg 66%▇ 0.9%blunt · at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted14.0% ✎▁▁·▁▁▂▃▃▃▁▁█ beats 20/56medium · avg 35%▇ 0.8%noisy
DecisionBench v1 · target selection (all-request accuracy) submitted5.0% ✎▁▁·▁▁▃▃▁▂▁▁█ beats 7/56hard · avg 29%▇ 0.8%noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted48.0% ✎▂·····▆█▂▂▄▇ beats 8/56easy · avg 77%▇ 0.7%at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted35.5% ✎▁▁▁▂▆▃▃█···▁ beats 9/56medium · avg 52%▇ 0.5%blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted53.0% ✎▁·▁▁·▁▁█▂▃█▂ beats 15/56easy · avg 71%▇ 0.4%blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted66.0% ✎▁····▃▅▃▂▂·█ beats 18/56easy · avg 82%▇ 0.4%at its level · noisy
DecisionBench v1 · context management (all-request accuracy) submitted58.5% ✎▁·····▁▇▆▁█▃ beats 18/56easy · avg 73%▇ 0.2%blunt · at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted0.0% ✎▃▁·▂▁▁▁▄▁▂▂█ beats 2/56hard · avg 21%▇ 0.2%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted10.9% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 5/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted5.9% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 2/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted54.6% ✎█▁···▁·▂▆▅▂▂ beats 33/56medium · 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/fastino ↗

$ 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= 20.4

$ 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