whatmodel.sh / decision / OpenThai-SystemOne (JevBench mini)

OpenThai-SystemOne (JevBench mini)

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

OpenThai-SystemOne (JevBench mini) is a source-available decision implementation from iApp Technology.

Catalogue identity notes

JevBench 0.1.0 mini tested configuration openthai-systemone: Decoder, trained scorer head; base Qwen3.5-0.8B-Base (Thai continued pre-training); readout 256-slot decision head; questions read as one causal sequence. Separate identity because the report does not establish equivalence to the newer Decision Index checkpoint or serving recipe. No latency imported.

46.1±2.3#236 of 355 decision modelsfrom 6 benchmark results across 1 source

$ how it compares

The decision models ranked either side of OpenThai-SystemOne (JevBench mini), out of 357 with a score.

#modelscorewhereRAMreleased
236Winnow-E4B EldanRing46±1model files
237Kas 4B kpiya46±1model files
238OpenThai-SystemOne (JevBench mini) iApp Technology46±2source code
239vera-core-2 scar-ai46±1model files
240Kev-4B (JevBench mini) Jared Palmer46±2source code

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

$ what it's good at

consistency▃·▂▂·▅▃·▃▅▃█ #12 of 21 · 61% of its score · 5 tests
testresultvs the others in its rundifficultycountswhy
JevBench mini 0.1.0 · Probability measure coherence (pass rate)39.7% ✎▄·▁·▃▃▁·▃▄▁█ beats 10/20medium · avg 43%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%sharp · at its level
JevBench mini 0.1.0 · Representation consistency (pass rate)76.9% ✎▃·▂·▂▂▂▃▅▅▃█ beats 10/20easy · avg 79%▇▇▇▇▇▇ 14%typical
JevBench mini 0.1.0 · Logical coherence (pass rate)61.3% ✎▃·▃·█▅▅██▃█▅ beats 1/20easy · avg 78%▇ 2.3%blunt
JevBench mini 0.1.0 · Choice-set coherence (pass rate)72.2% ✎▁▃▄█▄▄·····▄ beats 7/20easy · avg 79%▇ 1.2%noisy
JevBench mini 0.1.0 · Batch independence (pass rate)70.8% ✎▃··········█ beats 1/20very easy · avg 97%▇ 0.0%blunt · maxed out · noisy
other tests1 not in a task · 37% of its score
testresultvs the others in its rundifficultycountswhy
JevBench mini 0.1.0 · unchanged-answer accuracy82.4% ✎▁·▂·▂···▃▂▁█ beats 7/20very easy · avg 87%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%sharp

$ 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/iapp-technology ↗

$ 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

sourceresultsshare of the scorelicence
JevBench 0.1.0 mini evaluation reports6Apache-2.0
prior · pull toward the middle
weighted average= 46.1

$ 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