whatmodel.sh / decision / imajev-4b (DecisionBench 712891d1)

imajev-4b (DecisionBench 712891d1)

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

imajev-4b (DecisionBench 712891d1) is an open-weights decision model from mohit67890. Its published size is 4.690992128B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: mohit67890/imajev-4b, revision 712891d1192c6491441a19bdea254d8a6e1048d0; decision-model; adapter imajev-serving-systemone-v1; probability source trained_readout_4_rotation_mean_temperature_calibrated_v1. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported. 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 ↗

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

61.5±1.8#93 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of imajev-4b (DecisionBench 712891d1), out of 357 with a score, then more from mohit67890.

#modelscorewhereRAMreleased
91Wald-26B-A4B ORG2 AI62±1model files
92Blink v0.3 26B-A4B (NVFP4) Pixilab.ai62±1model files
93imajev-4b (DecisionBench 712891d1) mohit6789062±2model files
94GPT-6 Luna Decisions OpenAI62±1api price unknown2026-10-06
95Qwen Decision 27B noncausal LoRA jsaurabh61±1model files
more from mohit67890
108imajev-4b (DecisionBench c9e5f132) mohit6789061±2model files

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #20 of 114 · 99% of its score · 27 tests

Beats Nace.AI Drex Max v1 (27B), d1.1 (hosted), Span-02 (Gemma 4 26B-A4B) here, though they rank higher overall. Trails GPT-6 Luna Decisions here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · action selection (all-request accuracy) submitted63.7% ✎▂▁▂▃▄▃▁▁▂█▇▄ beats 48/56medium · avg 51%▇▇▇▇▇▇▇▇ 21%at its level
DecisionBench v1 · routing (all-request accuracy) submitted78.0% ✎▁▁▁▁▂▂▁▁▁▁▃█ beats 54/56medium · avg 64%▇▇▇▇▇ 12%sharp
DecisionBench v1 · record classification (all-request accuracy) submitted48.0% ✎▃▂▁▂▂▂▄▁▃▆██ beats 47/56medium · avg 39%▇▇▇▇ 10%at its level
DecisionBench v1 · navigation (all-request accuracy) submitted72.0% ✎▁▁·▃▁▁▁▁▁▁▃█ beats 44/56medium · avg 58%▇▇▇▇ 10%sharp
DecisionBench v1 · verification (all-request accuracy) submitted57.5% ✎▁▁▅▁▃▂▂▁▁▇▇█ beats 28/56medium · avg 56%▇▇▇ 6.8%blunt · at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted56.1% ✎▂▂·▁▂▄▃▆▄█▁▁ beats 47/56medium · avg 46%▇▇ 5.6%at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted62.3% ✎▁▁▅▅▃▃▅█▃▃·▁ beats 54/56medium · avg 45%▇▇ 4.8%at its level
DecisionBench v1 · triage (all-request accuracy) submitted85.0% ✎▁·▁·▂▃▄▃▂█▄▂ beats 38/56easy · avg 78%▇ 3.7%sharp
19 more tests
testresultvs the others in its rundifficultycountswhy
DecisionBench v1 · completion assessment (all-request accuracy) submitted90.0% ✎▁▁▂▃▄·▂▁▁▆█▂ beats 30/56very easy · avg 86%▇ 3.1%sharp · maxed out
DecisionBench v1 · review scoring (all-request accuracy) submitted59.0% ✎▁······▂▃▅▇█ beats 40/56medium · avg 52%▇ 3.1%at its level
DecisionBench v1 · content classification (all-request accuracy) submitted80.0% ✎▁····▁▁▁▁▁▁█ beats 44/56easy · avg 73%▇ 2.9%typical
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted62.0% ✎▁▁·▁▁▂▃▂▃▁▁█ beats 56/56medium · avg 35%▇ 2.6%at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted47.0% ✎▁▁·▁▁▁▃▁▂▁▁█ beats 45/56hard · avg 29%▇ 2.5%at its level · noisy
DecisionBench v1 · bounded extraction (all-request accuracy) submitted93.9% ✎▃▃▂·▁▁▁▁▁▁█▅ beats 38/56very easy · avg 86%▇ 2.3%sharp · maxed out · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted70.0% ✎▁▁·▁▂▂▁▃▃█▇▃ beats 49/56medium · avg 62%▇ 2.0%blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted68.0% ✎▂·▁▁▆█▅▃▃▂▁▁ beats 47/56medium · avg 52%▇ 1.3%at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted81.9% ✎█▄▃▁▁▃▂▃▁·▁▁ beats 50/56easy · avg 66%▇ 0.8%blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted87.9% ✎█▁▂▁▁▁▁▁▂▅▁▁ beats 49/56easy · avg 74%▇ 0.7%noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted62.4% ✎▁▁▁▂▆▃▃█···▁ beats 43/56medium · avg 52%▇ 0.6%blunt · at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted35.0% ✎▂▁·▂▁▁▁▄▁▂▂█ beats 48/56hard · avg 21%▇ 0.4%blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted95.0% ✎▂·····▆█▂▂▄▇ beats 41/56easy · avg 77%▇ 0.4%noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted84.0% ✎▁·▁▁·▁▁█▂▃█▂ beats 44/56easy · avg 71%▇ 0.3%blunt · noisy
DecisionBench v1 · context management (all-request accuracy) submitted88.5% ✎▁·····▁▇▆▁█▃ beats 39/56easy · avg 73%▇ 0.2%blunt · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted100.0% ✎▁····▃▅▃▂▂·█ beats 48/56easy · avg 82%▇ 0.2%noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted88.7% ✎▁·▁▄▇▄▅▄▃▁▄█ beats 36/56easy · avg 66%▇ 0.2%at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted86.9% ✎▃▃▄▅▆▂▅▄▃▄█▃ beats 36/56easy · avg 68%▇ 0.1%blunt · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted91.8% ✎█▁···▁·▂▆▅▂▃ beats 56/56medium · avg 42%▇ 0.0%blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. This is the revision recorded by the benchmark. 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/mohit67890 ↗

$ 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= 61.5

$ 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