whatmodel.sh / decision / SemIf (DecisionBench 1f2dea3e)

SemIf (DecisionBench 1f2dea3e)

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

SemIf (DecisionBench 1f2dea3e) is a source-available decision implementation from TheoLeeCJ. Its published size is 4.659865088B parameters.

Catalogue identity notes

DecisionBench v1 comparison: TheoLeeCJ/SemIf, revision 1f2dea3e25379f9dfc98cb83c324f00ab5deda37; language-model; adapter jev-compatible-server-v1; probability source option-letter-logit-softmax. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported.

Model information sources

· Parameter count ↗

Published served parameter count; not a RAM or download-size measurement.

53.6±1.7#178 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of SemIf (DecisionBench 1f2dea3e), out of 357 with a score, then more from TheoLeeCJ.

#modelscorewhereRAMreleased
178JPT-9B Qwen3.5-9B LoRA kirp54±1model files
179Saif 4B Gyr Technology54±1model files
180SemIf (DecisionBench 1f2dea3e) TheoLeeCJ54±2source code
181RSI-Jev v6.1 VL 4B shgao53±1model files2026-10-07
182PurpleMIST-Flash-1.0 Olaverse Lab53±1model files
more from TheoLeeCJ
242SemIf Qwen3.5-4B Base (decision readout) TheoLeeCJ46±1source code

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #58 of 114 · 99% of its score · 27 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, JevK5 v0.3, Together Tev1 Qwen3.5-4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted56.6% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 35/56medium · avg 51%▇▇▇▇▇▇▇▇ 20%at its level
DecisionBench v1 · routing (all-request accuracy) submitted66.0% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 28/56medium · avg 64%▇▇▇▇▇ 14%sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted40.0% ✎▁▁·▃▁▁▁▃▁▁▃█ beats 19/56medium · avg 58%▇▇▇▇ 11%sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted46.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 42/56medium · avg 39%▇▇▇▇ 8.9%at its level
DecisionBench v1 · verification (all-request accuracy) submitted62.5% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 46/56medium · avg 56%▇▇ 6.2%blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted55.5% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 46/56medium · avg 46%▇▇ 5.0%at its level
DecisionBench v1 · triage (all-request accuracy) submitted86.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 44/56easy · avg 78%▇▇ 4.5%sharp
DecisionBench v1 · completion assessment (all-request accuracy) submitted91.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 35/56very easy · avg 86%▇▇ 4.4%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted45.2% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 32/56medium · avg 45%▇▇ 4.2%at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted93.8% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 36/56very easy · avg 86%▇▇ 3.9%sharp · noisy
DecisionBench v1 · content classification (all-request accuracy) submitted79.0% ✎▁····▁▁▁▁▁▁█ beats 38/56easy · avg 73%▇ 3.4%typical
DecisionBench v1 · review scoring (all-request accuracy) submitted64.0% ✎▁······▂▃▅▇█ beats 54/56medium · avg 52%▇ 2.8%at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted11.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 15/56medium · avg 35%▇ 2.2%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted9.0% ✎▁▁·▁▁▁▃▁▂▁▁█ beats 16/56hard · avg 29%▇ 2.0%at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted71.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 52/56medium · avg 62%▇ 1.9%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted57.5% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 39/56medium · avg 52%▇ 1.2%at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted84.8% ✎█▁▂▁▁▁▁▁▃▅▁▁ beats 36/56easy · avg 74%▇ 0.8%noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted78.8% ✎█▄▃▁▁▃▃▂▁·▁▁ beats 46/56easy · avg 66%▇ 0.7%blunt · at its level
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted59.9% ✎▁▁▁▂▆▃▃█···▁ beats 34/56medium · avg 52%▇ 0.5%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted98.0% ✎▂·····▆█▂▂▄▇ beats 56/56easy · avg 77%▇ 0.4%noisy
DecisionBench v1 · document classification (all-request accuracy) submitted11.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 23/56hard · avg 21%▇ 0.3%blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted79.0% ✎▁·▁▁·▁▁█▂▃█▂ beats 33/56easy · avg 71%▇ 0.3%blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted100.0% ✎▁····▃▅▃▂▂·█ beats 52/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · context management (all-request accuracy) submitted91.5% ✎▁·····▁▇▆▁█▃ beats 49/56easy · avg 73%▇ 0.2%blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted50.2% ✎▁·▁▄▇▄▅▄▂▁▄█ beats 23/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted49.2% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 21/56easy · avg 68%▇ 0.1%blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted0.0% ✎█▁···▁·▂▆▅▂▂ beats 11/56medium · avg 42%▇ 0.0%blunt · at its level · noisy

$ 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/TheoLeeCJ ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 99%

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
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified27CC0 1.0
prior · pull toward the middle
weighted average= 53.6

$ 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