whatmodel.sh / decision / ZTC-Judge-4B (DecisionBench b0bb1603)

ZTC-Judge-4B (DecisionBench b0bb1603)

+ contribute

ZTC-Judge-4B (DecisionBench b0bb1603) is an open-weights decision model from FINAL-Bench. Its published size is 4.659865088B parameters. Licence: apache-2.0.

Catalogue identity notes

DecisionBench v1 comparison: FINAL-Bench/ZTC-Judge-4B, revision b0bb16038d7adbca6f4edda90ac72fb960d8319f; classifier; adapter jev-compatible-server-v1; probability source native_probability_distribution. 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.

28.5±1.6#318 of 355 decision modelsfrom 27 benchmark results across 1 source

$ how it compares

The decision models ranked either side of ZTC-Judge-4B (DecisionBench b0bb1603), out of 357 with a score, then more from FINAL-Bench.

#	model	score	where	released
318	Mola-68M codavidgarcia	29±1	model files	2026-10-14
319	JEV Ettin 400M Elfsong	29±1	model files
320	ZTC-Judge-4B (DecisionBench b0bb1603) FINAL-Bench	29±2	model files
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
	more from FINAL-Bench
196	ZTC-Judge-9B (DecisionBench 05d154a5) FINAL-Bench	51±2	model files

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

$ what it's good at

workflows▁▁▁▃▁▂▂▆█▄▁▁ #97 of 114 · 99% of its score · 27 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	27.3% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 12/56	medium · avg 51%	▇▇▇▇▇▇ 15%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	12.3% ✎	▁▃▁▁▂▂▁▁▁▁▃█ beats 2/56	medium · avg 64%	▇▇▇▇▇ 13%	sharp · at its level
DecisionBench v1 · completion assessment (all-request accuracy) submitted	69.0% ✎	▁▁▂▃▄·▃▁▁▆█▂ beats 18/56	very easy · avg 86%	▇▇▇▇ 11%	sharp · at its level
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	78.6% ✎	▃▃▂·▁▁▁▃▁▁█▅ beats 23/56	very easy · avg 86%	▇▇▇▇ 10%	sharp · at its level · noisy
DecisionBench v1 · navigation (all-request accuracy) submitted	16.0% ✎	▁▁·▃▁▁▁▁▁▁▃█ beats 8/56	medium · avg 58%	▇▇▇ 8.5%	sharp
DecisionBench v1 · triage (all-request accuracy) submitted	14.0% ✎	▁·▃·▂▃▄▃▂█▄▂ beats 2/56	easy · avg 78%	▇▇▇ 7.0%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	34.0% ✎	▃▂▁▂▂▂▄▃▃▆██ beats 22/56	medium · avg 39%	▇▇ 6.0%	typical
DecisionBench v1 · verification (all-request accuracy) submitted	42.0% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 14/56	medium · avg 56%	▇▇ 5.8%	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	60.0% ✎	▁····▁▁▁▁▁▃█ beats 17/56	easy · avg 73%	▇▇ 4.3%	at its level
DecisionBench v1 · document record classification (all-request accuracy) submitted	31.3% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 13/56	medium · avg 46%	▇▇ 3.9%	at its level
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	40.4% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 25/56	medium · avg 45%	▇ 3.3%	at its level
DecisionBench v1 · review scoring (all-request accuracy) submitted	43.0% ✎	▁······▂▃▅▇█ beats 21/56	medium · avg 52%	▇ 2.4%	at its level
DecisionBench v1 · risk scoring (all-request accuracy) submitted	30.0% ✎	▁▁·▃▂▂▁▃▃█▇▃ beats 3/56	medium · avg 62%	▇ 1.9%	blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted	35.3% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 13/56	medium · avg 52%	▇ 1.0%	at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	6.0% ✎	▁▁·▁▁▃▃▂▃▁▁█ beats 6/56	medium · avg 35%	▇ 1.0%	noisy
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	52.9% ✎	█▁▂▁▁▁▁▁▂▅▁▁ beats 21/56	easy · avg 74%	▇ 0.9%	at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	14.0% ✎	▁▁·▁▁▁▃▃▂▁▁█ beats 21/56	hard · avg 29%	▇ 0.9%	noisy
DecisionBench v1 · document workflows (all-request accuracy) submitted	46.9% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 2/56	easy · avg 66%	▇ 0.8%	blunt · at its level
DecisionBench v1 · safety gating (all-request accuracy) submitted	67.0% ✎	▂·····▆█▂▂▄▇ beats 28/56	easy · avg 77%	▇ 0.6%	at its level · noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	61.9% ✎	▁▁▁▂▆▃▃█···▁ beats 41/56	medium · avg 52%	▇ 0.5%	blunt · at its level · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	31.0% ✎	▁·▁▁·▃▁█▂▃█▂ beats 3/56	easy · avg 71%	▇ 0.3%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	81.0% ✎	▁····▃▅▃▂▂·█ beats 26/56	easy · avg 82%	▇ 0.3%	at its level · noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	20.0% ✎	▂▁·▂▁▁▁▄▁▃▂█ beats 29/56	hard · avg 21%	▇ 0.2%	blunt · noisy
DecisionBench v1 · context management (all-request accuracy) submitted	67.0% ✎	▁·····▁▇▆▁█▃ beats 26/56	easy · avg 73%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	38.2% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 18/56	easy · avg 66%	▇ 0.2%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	36.6% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 16/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	13.1% ✎	█▁···▃·▂▆▅▂▂ beats 19/56	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/FINAL-Bench ↗

$ 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		= 28.5

$ 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