whatmodel.sh / decision / NanoJev (DecisionBench 4a19595e)

NanoJev (DecisionBench 4a19595e)

+ contribute

NanoJev (DecisionBench 4a19595e) is an open-weights decision model from C-Tianyu. Its published size is 0.6B parameters.

Catalogue identity notes

DecisionBench v1 comparison: C-Tianyu/NanoJev, revision 4a19595eada0857133c0d2be024f879a4077054b; decision-model; adapter nanojev-hf; probability source native_candidate_logits_fp32_softmax. 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

· Parameter count ↗

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

19.4±1.8#344 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of NanoJev (DecisionBench 4a19595e), out of 357 with a score.

#	model	score	where
344	gliner2.5-base-v1 (DecisionBench 1a8bc24e) Fastino	20±2	model files
345	gliner2.5-multi-v1 (DecisionBench a221b77a) Fastino	20±2	model files
346	NanoJev (DecisionBench 4a19595e) C-Tianyu	19±2	model files
347	Bekko System One v0 17M hotchpotch	19±1	model files
348	bge-reranker-v2-m3 (DecisionBench 953dc6f6) BAAI	19±2	model files

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

$ what it's good at

workflows▁▁▃▂▁▂▂▆█▄▁▁ #107 of 114 · 99% of its score · 27 tests

Beats CLM-v0.1-8B Qwen3-8B heads here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · action selection (all-request accuracy) submitted	20.7% ✎	▂▁▃▃▄▃▁▁▂█▇▄ beats 4/56	medium · avg 51%	▇▇▇▇▇▇ 15%	typical
DecisionBench v1 · completion assessment (all-request accuracy) submitted	31.0% ✎	▁▁▃▃▄·▂▁▁▆█▂ beats 3/56	very easy · avg 86%	▇▇▇▇▇ 12%	sharp · at its level
DecisionBench v1 · routing (all-request accuracy) submitted	30.7% ✎	▁▁▁▁▂▃▁▁▁▁▃█ beats 13/56	medium · avg 64%	▇▇▇▇▇ 12%	sharp
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	22.4% ✎	▃▃▂·▁▁▁▁▁▁█▅ beats 4/56	very easy · avg 86%	▇▇▇ 8.6%	sharp · noisy
DecisionBench v1 · triage (all-request accuracy) submitted	36.0% ✎	▁·▁·▃▃▄▃▂█▄▂ beats 6/56	easy · avg 78%	▇▇▇ 7.6%	sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted	17.0% ✎	▁▁·▃▁▁▁▁▁▁▃█ beats 11/56	medium · avg 58%	▇▇▇ 7.0%	sharp
DecisionBench v1 · verification (all-request accuracy) submitted	35.0% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 8/56	medium · avg 56%	▇▇▇ 6.5%	blunt · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	17.0% ✎	▃▂▃▂▂▂▄▁▃▆██ beats 7/56	medium · avg 39%	▇▇ 5.9%	typical

19 more tests

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · content classification (all-request accuracy) submitted	38.0% ✎	▁····▁▁▁▃▁▁█ beats 9/56	easy · avg 73%	▇▇ 4.5%	at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	15.1% ✎	▂▃·▁▂▄▃▆▄█▁▁ beats 4/56	medium · avg 46%	▇▇ 4.0%	typical
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	24.5% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 3/56	medium · avg 45%	▇ 3.4%	typical
DecisionBench v1 · review scoring (all-request accuracy) submitted	41.0% ✎	▁······▂▃▅▇█ beats 19/56	medium · avg 52%	▇ 2.5%	at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted	41.0% ✎	▁▁·▁▂▃▁▃▃█▇▃ beats 9/56	medium · avg 62%	▇ 2.2%	blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	50.8% ✎	█▁▂▁▁▁▁▁▂▅▁▁ beats 12/56	easy · avg 74%	▇ 1.1%	at its level · noisy
DecisionBench v1 · reasoning (all-request accuracy) submitted	22.8% ✎	▂·▃▁▆█▅▃▃▂▁▁ beats 3/56	medium · avg 52%	▇ 1.1%	at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted	50.2% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 17/56	easy · avg 66%	▇ 0.9%	blunt · at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	10.0% ✎	▁▁·▁▁▂▃▂▃▁▁█ beats 13/56	medium · avg 35%	▇ 0.8%	noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	6.0% ✎	▁▁·▁▁▃▃▁▂▁▁█ beats 9/56	hard · avg 29%	▇ 0.8%	too hard for it · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted	0.0% ✎	▃·····▆█▂▂▄▇ beats 2/56	easy · avg 77%	▇ 0.7%	at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	61.7% ✎	▁▁▁▂▆▃▃█···▁ beats 38/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	3.0% ✎	▃·▁▁·▁▁█▂▃█▂ beats 0/56	easy · avg 71%	▇ 0.4%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	0.0% ✎	▃····▃▅▃▂▂·█ beats 2/56	easy · avg 82%	▇ 0.4%	at its level · noisy
DecisionBench v1 · context management (all-request accuracy) submitted	0.0% ✎	▃·····▁▇▆▁█▃ beats 2/56	easy · avg 73%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	7.0% ✎	▂▁·▂▁▁▃▄▁▂▂█ beats 14/56	hard · avg 21%	▇ 0.2%	blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	18.1% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 9/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	59.8% ✎	▃▃▄▅▆▃▅▄▃▄█▃ beats 24/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	45.0% ✎	█▁···▁·▃▆▅▂▂ beats 24/56	medium · avg 42%	▇ 0.0%	blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. 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/C-Tianyu ↗

$ 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

source	results	share of the score	licence
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified	27	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC0 1.0
prior · pull toward the middle		▇ 1%
weighted average		= 19.4

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-11-03 02:37 UTC · sources and licences · json