whatmodel.sh / decision / open-jev-deberta-v3-large (DecisionBench 19bf9a64)

open-jev-deberta-v3-large (DecisionBench 19bf9a64)

+ contribute

open-jev-deberta-v3-large (DecisionBench 19bf9a64) is an open-weights decision model from com-kotobalabs. Its published size is 0.43401216B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: com-kotobalabs/open-jev-deberta-v3-large, revision 19bf9a64815add579fbf6c907bef584d9277a8e4; decision-model; adapter openjev-hf; probability source native_grouped_logits_temperature_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.

27.2±1.6#321 of 355 decision modelsfrom 29 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of open-jev-deberta-v3-large (DecisionBench 19bf9a64), out of 357 with a score.

#	model	score	where	released
321	Jev-Style 0.8B v3 chaoliangUNSW	28±1	model files	2026-09-24
322	mxbai-rerank-base-v2 (DecisionBench 3ea9d4df) mixedbread-ai	27±2	model files
323	open-jev-deberta-v3-large (DecisionBench 19bf9a64) com-kotobalabs	27±2	model files
324	Crivo-32M v2 tardellirs	27±1	model files
325	LFM2.5-2.6B-RLCD monotykamary	26±1	model files

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

$ what it's good at

workflows▁▁▁▃▁▂▂▆█▄▁▁ #99 of 114 · 99% of its score · 28 tests

Trails GLiNER2.5-Decide 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	29.1% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 16/56	medium · avg 51%	▇▇▇▇▇▇ 15%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	32.3% ✎	▁▁▁▁▂▃▁▁▁▁▃█ beats 15/56	medium · avg 64%	▇▇▇▇▇ 12%	sharp · at its level
DecisionBench v1 · completion assessment (all-request accuracy) submitted	52.0% ✎	▁▁▂▃▄·▂▁▁▆█▂ beats 13/56	very easy · avg 86%	▇▇▇▇ 10%	sharp · at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	41.0% ✎	▃▃▃·▁▁▁▁▁▁█▅ beats 18/56	very easy · avg 86%	▇▇▇▇ 9.2%	sharp · at its level · noisy
DecisionBench v1 · navigation (all-request accuracy) submitted	18.0% ✎	▁▁·▃▃▁▁▁▁▁▃█ beats 12/56	medium · avg 58%	▇▇▇ 7.9%	sharp
DecisionBench v1 · triage (all-request accuracy) submitted	40.0% ✎	▁·▁·▂▃▄▃▂█▄▂ beats 7/56	easy · avg 78%	▇▇▇ 6.8%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	20.0% ✎	▃▂▁▃▂▂▄▁▃▆██ beats 10/56	medium · avg 39%	▇▇ 5.7%	typical
DecisionBench v1 · verification (all-request accuracy) submitted	46.0% ✎	▁▁▅▁▃▃▂▁▁▇▇█ beats 19/56	medium · avg 56%	▇▇ 5.6%	blunt · at its level

20 more tests

test	result	vs the others in its run	difficulty	counts	why
Chao Ma · clean support routing	84.0% ✎	█····█·····█ beats 0/2	very easy · avg 96%	▇▇ 4.4%	sharp · small run
DecisionBench v1 · content classification (all-request accuracy) submitted	67.0% ✎	▁····▁▁▁▁▁▃█ beats 20/56	easy · avg 73%	▇▇ 4.2%	at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	24.7% ✎	▂▂·▃▂▄▃▆▄█▁▁ beats 6/56	medium · avg 46%	▇ 3.7%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	25.8% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 8/56	medium · avg 45%	▇ 3.1%	at its level
DecisionBench v1 · review scoring (all-request accuracy) submitted	30.0% ✎	▁······▂▃▅▇█ beats 9/56	medium · avg 52%	▇ 2.3%	at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted	53.0% ✎	▁▁·▁▂▂▁▃▃█▇▃ beats 17/56	medium · avg 62%	▇ 1.9%	blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted	29.7% ✎	▂·▁▃▆█▅▃▃▂▁▁ beats 5/56	medium · avg 52%	▇ 1.0%	at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	11.0% ✎	▁▁·▁▁▂▃▂▃▁▁█ beats 14/56	medium · avg 35%	▇ 0.9%	noisy
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	59.9% ✎	█▁▃▁▁▁▁▁▂▅▁▁ beats 24/56	easy · avg 74%	▇ 0.9%	at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	10.0% ✎	▁▁·▁▁▁▃▃▂▁▁█ beats 19/56	hard · avg 29%	▇ 0.9%	noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted	66.5% ✎	█▄▃▃▁▃▂▂▁·▁▁ beats 36/56	easy · avg 66%	▇ 0.8%	blunt · at its level
DecisionBench v1 · safety gating (all-request accuracy) submitted	0.0% ✎	▃·····▆█▂▂▄▇ beats 0/56	easy · avg 77%	▇ 0.6%	at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	53.0% ✎	▁▁▁▂▆▃▃█···▁ beats 30/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	11.0% ✎	▁·▃▁·▁▁█▂▃█▂ beats 1/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	0.0% ✎	▃····▃▅▃▂▂·█ beats 0/56	easy · avg 82%	▇ 0.3%	at its level · noisy
DecisionBench v1 · context management (all-request accuracy) submitted	0.0% ✎	▃·····▁▇▆▁█▃ beats 0/56	easy · avg 73%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	11.0% ✎	▂▁·▂▁▁▁▄▁▂▂█ beats 21/56	hard · avg 21%	▇ 0.2%	blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	40.1% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 19/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	49.9% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 23/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	1.4% ✎	█▃···▁·▂▆▅▂▂ beats 17/56	medium · avg 42%	▇ 0.0%	blunt · at its level · noisy

consistency█····█·····█ #1 of 3 * · 0.1% of its score · 1 test

Beats Jev 1.13, decider-2b (DecisionBench fa996cea) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Chao Ma · confidence under authority injection	0.5714 auroc ✎	█····█·····█ beats 2/2	avg 0.426 auroc	▇ 0.1%	blunt · small run

$ 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/com-kotobalabs ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 94%, Chao Ma · independent injecti… 4%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%	CC0 1.0
Chao Ma · independent injection study	2	▇ 4%	MIT
prior · pull toward the middle		▇ 1%
weighted average		= 27.2

$ 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