whatmodel.sh / decision / Jebadiah 9B v2 (JevBench mini)
Jebadiah 9B v2 (JevBench mini)
↗ share
+ contribute
Jebadiah 9B v2 (JevBench mini) is a source-available decision implementation from Frontier Infra.
Catalogue identity notes
JevBench 0.1.0 mini tested configuration jebadiah-9b: Decoder, answer-letter logits; base Qwen3.5-9B; readout merged LoRA, per-type temperatures. 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 Jebadiah 9B v2 (JevBench mini), out of 357 with a score.
| # | model | score | where |
|---|---|---|---|
| 186 |  Bespoke-Nimble-9B (JevBench mini) | 53±2 | source code |
| 187 |  Hopper 12B (trained) | 52±1 | model files |
| 188 | Jebadiah 9B v2 (JevBench mini) | 52±2 | source code |
| 189 | jiwo 4B v2 | 52±1 | model files |
| 190 |  baselabs joey-1 (2B) | 52±1 | api price unknown |
see all decision models · find the ones that fit your machine
$ what it's good at
consistency▃·▂▂·▅▃·▃▅▃█ #7 of 21 · 68% of its score · 5 tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · Probability measure coherence (pass rate) | 48.0% ✎ | ▄·▁·▃▃▁·▃▄▃█ beats 14/20 | 51% |
| JevBench mini 0.1.0 · Representation consistency (pass rate) | 79.2% ✎ | ▃·▂·▂▂▂▃▅▅▃█ beats 13/20 | 13% |
| JevBench mini 0.1.0 · Logical coherence (pass rate) | 83.8% ✎ | ▃·▃·█▅▅██▃█▅ beats 16/20 | 2.3% |
| JevBench mini 0.1.0 · Choice-set coherence (pass rate) | 73.6% ✎ | ▁▃▄█▄▄·····▄ beats 8/20 | 1.2% |
| JevBench mini 0.1.0 · Batch independence (pass rate) | 100.0% ✎ | ▁··········█ beats 14/20 | 0.0% |
other tests1 not in a task · 30% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| JevBench mini 0.1.0 · unchanged-answer accuracy | 89.1% ✎ | ▁·▂·▂···▂▂▁█ beats 19/20 | 30% |
$ 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/getainode ↗
$ 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 | = 52.4 |
$ 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