whatmodel.sh / decision / QEV-2B
QEV-2B
↗ share
+ contribute
QEV-2B is an open-weights decision model from ken-jo. Its published size is 2.21B parameters. Licence: apache-2.0.
Catalogue identity notes
Exact Decision Index tested engine qev-2b; reported model QEV-2B. 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.
$ how it compares
The decision models ranked either side of QEV-2B, out of 357 with a score, then more from ken-jo.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 189 | jiwo 4B v2 | 52±1 | model files | ||
| 190 |  baselabs joey-1 (2B) | 52±1 | api price unknown | ||
| 191 | QEV-2B | 52±4 | model files | ||
| 192 |  Jebadiah 4B v2 (Ollaya Q8_0) | 52±3 | local | ||
| 193 |  JEV-9B | 52±1 | model files | ||
| more from ken-jo | |||||
| 250 | QEV-0.8B | 44±4 | model files | ||
see all decision models · find the ones that fit your machine
$ what it's good at
vision▁·▃▂▃▃▇▄▄█▄▃ #59 of 79 · 95% of its score · 12 tests
Trails RSI-Jev v5.0 VL 3B, Valen-4B, InternLM Intern-Decision Qwen3.5-4B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted | 83.5600 points ✎ | ▁·▁▁▃▁▄▄▃▅█▂ beats 46/61 | 12% |
| Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted | 16.0000 points ✎ | ▁▁▅▁▄▁▄█▄▃▇▇ beats 13/61 | 11% |
| Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted | 65.5000 points ✎ | ▁·▁▁▁▁·▃▁▃▅█ beats 14/61 | 10% |
| Decision Index Vision 0.4: private same skills (points) | 48.2800 points ✎ | ▁▁▃▃▁▂▄▆▃▃▅█ beats 17/61 | 10% |
| Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted | 31.5700 points ✎ | ▆▃▃▆▄▄▇██▁▆▆ beats 23/61 | 8.8% |
| Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted | 55.3300 points ✎ | ▁·▂▂▁▃▃▅▅▃▂█ beats 19/61 | 8.0% |
| Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted | 65.6600 points ✎ | ▂▁▁▁▁▃▁▅▅▆██ beats 19/61 | 7.8% |
| Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted | 81.4200 points ✎ | ▁·▁▂▁▁▃▁▂▂▅█ beats 13/61 | 6.2% |
4 more tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted | 15.3600 points ✎ | ▂▄▇▆█▄▄▇▂··▁ beats 10/61 | 6.2% |
| Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted | 47.9700 points ✎ | ▁···▁▂▂▃█▄▂▃ beats 15/61 | 5.9% |
| Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted | 71.8300 points ✎ | ▁▁▁▁▂▁▁▁▄█▃▃ beats 19/61 | 4.7% |
| Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted | 92.5900 points ✎ | ▁··▁▁▁▁▁▂▄█▁ beats 46/61 | 3.4% |
$ 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/ken-jo ↗
$ 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
| source | results | share of the score |
|---|---|---|
 Decision Index Vision 0.4 · submitted; independent execution unverified | 12 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 52.1 |
$ improve this page
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