whatmodel.sh / decision / RBDash-Decision v0.2

RBDash-Decision v0.2

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

RBDash-Decision v0.2 is an open-weights decision model from RBDash-Team. Its published size is 26.09B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine rbdash-decision-v0.2; reported model RBDash-Decision v0.2. Type: full fine-tune; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark. 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 ↗

Publisher parameter count; includes the served backbone, not just adapter size.

67.7±3.5#34 of 355 decision modelsfrom 12 benchmark results across 1 source

$ how it compares

The decision models ranked either side of RBDash-Decision v0.2, out of 357 with a score.

#modelscorewhereRAMreleased
32d1.1 (hosted) Liquid AI68±2api price unknown
33VisionJEV 1.0.0 (27B) taoszhang68±1model files
34RBDash-Decision v0.2 RBDash-Team68±4model files
35mogan-decision-31B-it Mogan AI67±1model files
36oenogarum (Gemma 4 31B) plantwaterer67±1model files

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

$ what it's good at

vision▁·▃▂▃▃▇▄▄█▄▃ #12 of 79 · 95% of its score · 12 tests

Beats Fastino GLiDE 1.2, StartLux-Decision v1.1 27B, vLLM-SR d3-turbo v1.1 (27B) here, though they rank higher overall. Trails Mercury Decide (free endpoint), Clef, Jev 1.14 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted87.6700 points ✎▁·▁▁▃▁▄▄▃▅█▂ beats 57/61avg 63.423 points▇▇▇▇▇ 12%blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted44.4400 points ✎▁▁▅▁▄▁▄█▄▃▇▇ beats 52/61avg 22.797 points▇▇▇▇ 11%blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted87.0000 points ✎▁·▁▁▁▁·▂▁▃▅█ beats 59/61avg 66.987 points▇▇▇▇ 10%blunt
Decision Index Vision 0.4: private same skills (points)68.9100 points ✎▁▁▃▃▁▂▄▆▃▃▅█ beats 58/61avg 48.067 points▇▇▇▇ 10%blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted57.6300 points ✎▆▃▃▆▄▄▇██▁▆▆ beats 60/61avg 28.443 points▇▇▇▇ 8.8%blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted73.3600 points ✎▁·▂▂▁▃▃▅▅▃▂█ beats 53/61avg 53.651 points▇▇▇ 8.0%blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted79.2000 points ✎▂▁▁▁▁▃▁▅▅▆██ beats 45/61avg 62.137 points▇▇▇ 7.8%blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted97.8100 points ✎▁·▁▂▁▁▃▁▂▂▅█ beats 50/61avg 83.859 points▇▇ 6.2%blunt
4 more tests
testresultvs the others in its rundifficultycountswhy
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted35.2100 points ✎▂▄▇▆█▄▄▇▂··▁ beats 49/61avg 19.676 points▇▇ 6.2%blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted75.3500 points ✎▁···▁▂▂▂█▄▂▃ beats 60/61avg 44.994 points▇▇ 5.9%blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted77.8200 points ✎▁▁▁▁▂▁▁▁▄█▃▃ beats 53/61avg 67.662 points▇▇ 4.7%blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted92.9900 points ✎▁··▁▁▁▁▁▂▄█▁ beats 57/61avg 85.184 points▇ 3.4%blunt

$ where to run it

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. 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/RBDash-Team ↗

$ how the score was worked out · Decision Index Vision 0.4 95%

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
Decision Index Vision 0.4 · submitted; independent execution unverified12CC BY 4.0
prior · pull toward the middle
weighted average= 67.7

$ 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