whatmodel.sh / decision / laya-typed-decisions (DecisionBench bc76315b)

laya-typed-decisions (DecisionBench bc76315b)

+ contribute

laya-typed-decisions (DecisionBench bc76315b) is an open-weights decision model from ConvAI Innovations. Its published size is 0.42129383B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: convaiinnovations/laya-typed-decisions, revision bc76315b568af04bc19f133c8bca9a2b3a2d9905; decision-model; adapter laya-native-build-sequence-v1; probability source native-option-marker-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

· Weights licence ↗ · Parameter count ↗

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

29.4±1.5#313 of 355 decision modelsfrom 29 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of laya-typed-decisions (DecisionBench bc76315b), out of 357 with a score, then more from ConvAI Innovations.

#	model	score	where	RAM
313	GLiNER2.5-Decide (DecisionBench 0872ab14) Fastino	30±2	model files
314	LiquidAI d1-omni-600M Liquid AI	30±1	local	~2.7GB
315	laya-typed-decisions (DecisionBench bc76315b) ConvAI Innovations	29±2	model files
316	Bosun v3.1 1.7B LoRA Hanno Labs	29±1	model files
317	vLLM-SR Decision 2.0 Kai 0.6B vLLM Semantic Router	29±1	local	~3.7GB
	more from ConvAI Innovations
331	laya (DecisionBench 1c5edc17) ConvAI Innovations	25±1	local	~1.7GB
340	Laya ConvAI Innovations	21±1	model files

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

$ what it's good at

workflows▁▁▁▃▁▂▂▆█▄▁▁ #96 of 114 · 99% of its score · 29 tests

Trails GLiNER2.5-Decide, vLLM-SR Decision 2.0 Kai 0.6B 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	28.1% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 14/56	medium · avg 51%	▇▇▇▇▇▇ 14%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	41.7% ✎	▁▁▁▁▂▂▃▁▁▁▃█ beats 18/56	medium · avg 64%	▇▇▇▇▇ 12%	sharp · at its level
DecisionBench v1 · completion assessment (all-request accuracy) submitted	39.0% ✎	▁▁▂▃▄·▂▁▁▆█▂ beats 7/56	very easy · avg 86%	▇▇▇▇ 10%	sharp · at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	26.4% ✎	▃▃▂·▁▁▁▁▁▁█▅ beats 9/56	very easy · avg 86%	▇▇▇▇ 8.8%	sharp · at its level · noisy
DecisionBench v1 · navigation (all-request accuracy) submitted	24.0% ✎	▁▁·▃▁▃▁▁▁▁▃█ beats 16/56	medium · avg 58%	▇▇▇ 7.9%	sharp · at its level
Privacy policy · diagnostic43	30.2% ✎	█········▄·▄ beats 1/3	easy · avg 70%	▇▇▇ 6.5%	sharp · at its level
DecisionBench v1 · triage (all-request accuracy) submitted	59.0% ✎	▁·▁·▂▃▄▃▂█▄▂ beats 18/56	easy · avg 78%	▇▇▇ 6.3%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	28.0% ✎	▃▂▁▂▂▂▄▁▃▆██ beats 19/56	medium · avg 39%	▇▇ 5.5%	typical

21 more tests

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · verification (all-request accuracy) submitted	42.5% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 15/56	medium · avg 56%	▇▇ 5.3%	blunt · at its level
DecisionBench v1 · content classification (all-request accuracy) submitted	53.0% ✎	▁····▁▁▁▁▃▁█ beats 15/56	easy · avg 73%	▇▇ 3.9%	at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	33.4% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 16/56	medium · avg 46%	▇ 3.6%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	31.1% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 18/56	medium · avg 45%	▇ 3.0%	at its level
Privacy policy · challenge56	28.6% ✎	▄·······▄··█ beats 0/3	very easy · avg 97%	▇ 2.2%	sharp · at its level · noisy
DecisionBench v1 · review scoring (all-request accuracy) submitted	40.0% ✎	▁······▂▃▅▇█ beats 18/56	medium · avg 52%	▇ 2.2%	at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted	51.0% ✎	▁▁·▁▂▂▁▃▃█▇▃ beats 14/56	medium · avg 62%	▇ 1.7%	blunt · at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	12.0% ✎	▁▁·▁▁▂▃▂▃▁▁█ beats 17/56	medium · avg 35%	▇ 0.9%	noisy
DecisionBench v1 · reasoning (all-request accuracy) submitted	37.0% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 15/56	medium · avg 52%	▇ 0.9%	at its level
DecisionBench v1 · target selection (all-request accuracy) submitted	16.0% ✎	▁▁·▁▁▁▃▁▃▁▁█ beats 24/56	hard · avg 29%	▇ 0.9%	noisy
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	77.8% ✎	█▁▂▁▁▁▃▁▂▅▁▁ beats 33/56	easy · avg 74%	▇ 0.8%	at its level · noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted	52.1% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 24/56	easy · avg 66%	▇ 0.7%	blunt · at its level
DecisionBench v1 · safety gating (all-request accuracy) submitted	63.0% ✎	▂·····▆█▂▂▄▇ beats 24/56	easy · avg 77%	▇ 0.6%	at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	58.8% ✎	▁▁▁▂▆▃▃█···▁ beats 33/56	medium · avg 52%	▇ 0.4%	blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	87.0% ✎	▁·▁▁·▁▁█▂▃█▃ beats 52/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	88.0% ✎	▁····▃▅▃▃▂·█ beats 30/56	easy · avg 82%	▇ 0.3%	at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	2.0% ✎	▂▁·▃▁▁▁▄▁▂▂█ beats 5/56	hard · avg 21%	▇ 0.2%	blunt · noisy
DecisionBench v1 · context management (all-request accuracy) submitted	55.5% ✎	▁·····▁▇▆▁█▃ beats 17/56	easy · avg 73%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	22.2% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 13/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	28.5% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 12/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	42.1% ✎	█▁···▁·▃▆▅▂▂ beats 23/56	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/convaiinnovations ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 90%, FloorIsAwake · Privacy Decisi… 9%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%	CC0 1.0
FloorIsAwake · Privacy Decision Benchmark	2	▇▇▇ 9%	MIT
prior · pull toward the middle		▇ 1%
weighted average		= 29.4

$ 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