whatmodel.sh / decision / jev-d3-46k

jev-d3-46k

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

jev-d3-46k is an open-weights decision model from tinnel123. Its published size is 26.09B parameters.

Catalogue identity notes

Exact Decision Index tested engine jev-d3-46k; reported model jev-d3-46k. 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

· Parameter count ↗

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

58.6±3.5#122 of 355 decision modelsfrom 12 benchmark results across 1 source

$ how it compares

The decision models ranked either side of jev-d3-46k, out of 357 with a score.

#modelscorewhereRAMreleased
122Decider chat · Qwen3.6-27B (decision readout) Mapika59±1source code
123Xor 1.2 Juspay Technologies59±1model files2026-09-28
124jev-d3-46k tinnel12359±4model files
125Jebadiah 27B v2.1 (Ollaya Q4_K_M) frontier-infra59±4local~16GB2026-10
126vLLM-SR d3-mini (4B) vLLM Semantic Router58±1local~11GB

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

$ what it's good at

vision▁·▃▂▃▃▇▄▄█▄▃ #39 of 79 · 95% of its score · 12 tests

Beats Surogate Rune 26B-A4B v3, Clef-omni here, though they rank higher overall. Trails Clef-flash here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted77.6600 points ✎▁·▁▁▃▁▄▄▃▅█▂ beats 36/61avg 63.423 points▇▇▇▇▇ 12%blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted32.1100 points ✎▁▁▅▁▄▁▄█▄▃▇▇ beats 33/61avg 22.797 points▇▇▇▇ 11%blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted80.7500 points ✎▁·▁▁▁▁·▂▁▃▅█ beats 34/61avg 66.987 points▇▇▇▇ 10%blunt
Decision Index Vision 0.4: private same skills (points)59.0800 points ✎▁▁▃▃▁▂▄▆▃▃▅█ beats 37/61avg 48.067 points▇▇▇▇ 10%blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted45.4200 points ✎▆▃▃▆▄▄▇██▁▆▆ beats 48/61avg 28.443 points▇▇▇▇ 8.8%blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted58.3800 points ✎▁·▂▂▁▃▃▅▅▃▂█ beats 25/61avg 53.651 points▇▇▇ 8.0%blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted72.6800 points ✎▂▁▁▁▁▃▁▅▅▆██ beats 33/61avg 62.137 points▇▇▇ 7.8%blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted91.2600 points ✎▁·▁▂▁▁▃▁▂▃▅█ beats 29/61avg 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) submitted17.1600 points ✎▂▄▇▆█▄▄▇▂··▁ beats 17/61avg 19.676 points▇▇ 6.2%blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted55.0500 points ✎▁···▁▂▂▂█▄▂▃ beats 36/61avg 44.994 points▇▇ 5.9%blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted74.5800 points ✎▁▁▁▁▂▁▁▁▄█▃▃ beats 29/61avg 67.662 points▇▇ 4.7%blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted91.8500 points ✎▁··▁▁▁▁▁▂▄█▁ beats 35/61avg 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/tinnel123 ↗

$ 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= 58.6

$ 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