whatmodel.sh / decision / smalljev-semantic-v9 (DecisionBench 8e2bac7c)

smalljev-semantic-v9 (DecisionBench 8e2bac7c)

+ contribute

smalljev-semantic-v9 (DecisionBench 8e2bac7c) is an open-weights decision model from isHeSatoshi.

Catalogue identity notes

DecisionBench v1 comparison: isHeSatoshi/smalljev-semantic-v9, revision 8e2bac7c4e922371c05899f4f000233e8096fee6; classifier; adapter jev-compatible-server-smalljev-v9-aux-heads-grouped-v1; probability source published-auxiliary-heads-and-grouped-choice-reconstruction. 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.

35.7±1.6#280 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of smalljev-semantic-v9 (DecisionBench 8e2bac7c), out of 357 with a score.

#	model	score	where	RAM	released
280	InternLM Intern-Decision Qwen3.5-2B Shanghai AI Laboratory (InternLM)	37±1	model files
281	Sieve 2B Sthānika AI	37±1	model files		2026-10-13
282	smalljev-semantic-v9 (DecisionBench 8e2bac7c) isHeSatoshi	36±2	model files
283	Strands Decider 2B (Hobson v21) Amazon Web Services	36±1	local	~6.6GB	2026-10
284	vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B) vLLM Semantic Router	35±1	model files

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

$ what it's good at

workflows▁▁▁▂▃▂▂▆█▄▁▁ #93 of 114 · 99% of its score · 27 tests

Trails GLiNER2.5-Decide, vLLM-SR Decision 2.0 Kai 0.6B, LiquidAI d1-omni-600M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · action selection (all-request accuracy) submitted	35.6% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 20/56	medium · avg 51%	▇▇▇▇▇▇▇ 16%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	51.0% ✎	▁▁▁▁▂▂▁▃▁▁▃█ beats 21/56	medium · avg 64%	▇▇▇▇▇ 14%	sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted	41.0% ✎	▁▁·▃▁▁▁▃▁▁▃█ beats 21/56	medium · avg 58%	▇▇▇▇ 10%	sharp · at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	55.5% ✎	▃▃▂·▃▁▁▁▁▁█▅ beats 19/56	very easy · avg 86%	▇▇▇▇ 8.9%	sharp · at its level · noisy
DecisionBench v1 · completion assessment (all-request accuracy) submitted	80.0% ✎	▁▁▂▃▄·▂▃▁▆█▂ beats 22/56	very easy · avg 86%	▇▇▇▇ 8.8%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	29.0% ✎	▃▂▁▂▂▂▄▁▃▆██ beats 20/56	medium · avg 39%	▇▇▇ 6.5%	at its level
DecisionBench v1 · triage (all-request accuracy) submitted	36.0% ✎	▁·▁·▃▃▄▃▂█▄▂ beats 4/56	easy · avg 78%	▇▇▇ 6.4%	sharp · at its level
DecisionBench v1 · verification (all-request accuracy) submitted	48.0% ✎	▁▁▅▁▃▂▃▁▁▇▇█ beats 21/56	medium · avg 56%	▇▇ 5.6%	blunt · at its level

19 more tests

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · content classification (all-request accuracy) submitted	62.0% ✎	▁····▁▁▁▁▁▃█ beats 18/56	easy · avg 73%	▇▇ 4.1%	at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	36.2% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 20/56	medium · avg 46%	▇▇ 4.0%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	36.0% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 23/56	medium · avg 45%	▇ 3.4%	at its level
DecisionBench v1 · review scoring (all-request accuracy) submitted	20.0% ✎	▁······▃▃▅▇█ beats 3/56	medium · avg 52%	▇ 2.4%	at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted	21.0% ✎	▁▃·▁▂▂▁▃▃█▇▃ beats 1/56	medium · avg 62%	▇ 1.8%	blunt · at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	28.0% ✎	▁▁·▁▁▂▃▂▃▃▁█ beats 31/56	medium · avg 35%	▇ 1.3%	noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	29.0% ✎	▁▁·▁▁▁▃▁▂▃▁█ beats 30/56	hard · avg 29%	▇ 1.1%	noisy
DecisionBench v1 · reasoning (all-request accuracy) submitted	34.2% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 11/56	medium · avg 52%	▇ 1.0%	at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	49.0% ✎	█▁▂▁▁▁▁▁▂▅▁▁ beats 3/56	easy · avg 74%	▇ 0.8%	at its level · noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted	49.7% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 15/56	easy · avg 66%	▇ 0.7%	blunt · at its level
DecisionBench v1 · safety gating (all-request accuracy) submitted	56.0% ✎	▂·····▆█▂▂▄▇ beats 17/56	easy · avg 77%	▇ 0.6%	at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	64.4% ✎	▁▁▁▂▆▃▃█···▁ beats 55/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	51.0% ✎	▁·▁▁·▁▁█▂▃█▂ beats 12/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	45.0% ✎	▁····▃▅▃▂▂·█ beats 7/56	easy · avg 82%	▇ 0.3%	at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	19.0% ✎	▂▁·▂▁▁▁▄▁▃▂█ beats 28/56	hard · avg 21%	▇ 0.2%	blunt · noisy
DecisionBench v1 · context management (all-request accuracy) submitted	53.0% ✎	▁·····▁▇▆▁█▃ beats 12/56	easy · avg 73%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	45.3% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 20/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	79.5% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 30/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	67.9% ✎	█▁···▁·▂▆▅▂▂ beats 41/56	medium · 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/isHeSatoshi ↗

$ 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		= 35.7

$ 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