whatmodel.sh / decision / OneJev-4B (JevBench mini)
OneJev-4B (JevBench mini)
↗ share
+ contribute
OneJev-4B (JevBench mini) is a source-available decision implementation from OmniJev.
Catalogue identity notes
JevBench 0.1.0 mini tested configuration onejev-4b: Decoder, answer-letter logits; base Qwen3.5-4B; readout full fine-tune (vision tower frozen); option-letter probability. Separate identity because the report does not establish equivalence to the newer Decision Index checkpoint or serving recipe. No latency imported.
$ how it compares
The decision models ranked either side of OneJev-4B (JevBench mini), out of 357 with a score, then more from OmniJev.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 201 | Decider 4B | 51±1 | local | ||
| 202 |  Together Tev1 Qwen3.5-4B | 51±1 | model files | ||
| 203 | OneJev-4B (JevBench mini) | 51±2 | source code | ||
| 204 |  JPT-4B Qwen3.5-4B LoRA | 50±1 | model files | ||
| 205 |  Bespoke Nimble 9B v2 | 50±1 | local | ||
| more from OmniJev | |||||
| 23 | OneJev1.6-27B | 69±2 | model files | ||
| 58 | OneJev1.5-27B | 65±4 | model files | ||
| 68 | OneJev1.6-9B | 64±1 | model files | ||
see all decision models · find the ones that fit your machine
$ what it's good at
consistency▃·▂▂·▅▃·▃▅▃█ #8 of 21 · 66% of its score · 5 tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · Probability measure coherence (pass rate) | 43.6% ✎ | ▄·▁·▃▃▁·▃▄▁█ beats 12/20 | 49% |
| JevBench mini 0.1.0 · Representation consistency (pass rate) | 79.7% ✎ | ▃·▂·▂▂▂▃▅▅▃█ beats 14/20 | 13% |
| JevBench mini 0.1.0 · Logical coherence (pass rate) | 71.3% ✎ | ▃·▃·█▅▅██▃█▅ beats 6/20 | 2.3% |
| JevBench mini 0.1.0 · Choice-set coherence (pass rate) | 68.1% ✎ | ▁▃▄█▄▄·····▄ beats 4/20 | 1.2% |
| JevBench mini 0.1.0 · Batch independence (pass rate) | 100.0% ✎ | ▁··········█ beats 11/20 | 0.0% |
other tests1 not in a task · 32% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · unchanged-answer accuracy | 89.2% ✎ | ▁·▂·▂···▂▂▁█ beats 20/20 | 32% |
$ where to run it
Implementation and setup instructions ↗
Published implementation and setup documentation verified. This entry describes a decision readout or evaluated configuration, not necessarily separate trained weights. Follow the referenced version and model settings; hardware compatibility has not been verified. Source · checked 2026-10-31.
Model repository and documentation: github.com/OmniJev ↗
$ how the score was worked out · JevBench 0.1.0 mini evaluatio… 98%
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 |
|---|---|---|
 JevBench 0.1.0 mini evaluation reports | 6 | 98% |
| prior · pull toward the middle | 2% | |
| weighted average | = 50.6 |
$ 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