JJ-1

日本語 · JurinAI on Hugging Face · JJ-1 article: English / 日本語

Japanese business decision models.

JJ-1 is JurinAI's model family for routing requests, judging urgency and deciding what needs follow-up. Give it a state — text or JSON — and typed questions; it returns structured answers and probabilities, without generating prose.

• Choice — select an option and return its probability distribution.
• Yes / no — return the probability of yes.
• Score — return a probability-weighted level on an ordered scale.

This is the central hub for the JJ-1 family. Each model has its own repository for weights, a model card and inference instructions.

Models

Four sizes share the same decision interface. Start with the smallest model that meets your workflow's accuracy requirements.

• JJ-1-0.8B
• JJ-1-2B
• JJ-1-4B
• JJ-1-9B

Access: the linked model repositories are currently private.

Full dataset evaluation

The JJ-1 report evaluates six areas: Japanese enterprise workflows; news, tools and safety; Japanese knowledge and reasoning; English knowledge and classification; emotion and scenario classification; and Japanese semantic similarity.

The evaluation contains 88,813 questions. Accuracy is weighted by question count over 84,153 hard-label questions; 4,660 soft-label questions are evaluated separately.

Model	Overall	English	Japanese
JJ-1-0.8B	65.49%	78.66%	57.34%
JJ-1-2B	68.54%	78.09%	62.63%
JJ-1-4B	75.18%	82.25%	70.80%
JJ-1-9B	79.20%	84.92%	75.66%

JJ-1-9B reaches 79.20% overall and 75.66% Japanese accuracy in this evaluation. Validate performance on your own workflow.

Results by evaluation area

Comparison of the 17 models with complete results across all six areas in the report. Values are hard-label accuracy (%); Overall is weighted by question count. Soft-label questions are excluded from this table.

Column	Evaluation area	All questions	Hard-label questions
01	Japanese enterprise workflows	6,249	6,033
02	News, tools & safety	10,967	10,967
03	Japanese knowledge & reasoning	45,391	45,391
04	English knowledge & classification	22,417	19,115
05	Emotion & scenario classification	2,200	2,200
06	Japanese semantic similarity	1,589	447

Model	Overall	01	02	03	04	05	06
JJ-1-9B	79.20%	97.43%	92.17%	72.70%	81.31%	80.50%	79.19%
StartLux 9B	78.02%	90.10%	92.36%	71.29%	81.73%	80.86%	73.60%
Jev 1.13	76.50%	91.75%	89.81%	71.96%	76.82%	60.32%	70.92%
Microsoft Decision-1	76.50%	91.58%	90.53%	69.76%	81.22%	63.45%	74.50%
JJ-1-4B	75.18%	96.17%	90.89%	67.29%	78.72%	70.41%	78.97%
StartLux 4B	74.54%	89.34%	91.47%	66.55%	79.63%	71.68%	67.34%
JPT 9B	73.45%	89.36%	90.43%	66.51%	76.54%	61.86%	71.14%
Nimble 9B v3	72.00%	89.21%	84.95%	65.04%	77.08%	60.32%	69.13%
JevK5 9B	71.77%	87.58%	89.09%	65.16%	74.15%	58.27%	69.35%
GPT-6 Luna Decisions	71.35%	91.99%	86.79%	65.07%	72.16%	59.41%	75.17%
Jebadiah 9B v2	70.82%	88.36%	87.72%	63.09%	75.49%	59.50%	61.74%
JPT 4B	70.62%	87.15%	90.26%	62.32%	75.15%	61.86%	57.72%
Kev 9B	70.08%	85.61%	89.24%	62.37%	74.13%	57.27%	63.98%
JJ-1-2B	68.54%	94.63%	87.35%	58.19%	73.42%	73.00%	75.39%
StartLux 2B	68.24%	82.51%	89.22%	57.78%	75.80%	75.55%	63.98%
StartLux 0.8B	65.64%	76.99%	88.91%	53.74%	74.44%	88.23%	63.31%
JJ-1-0.8B	65.49%	92.31%	87.33%	52.43%	72.62%	88.50%	75.62%

Column 06 is the report’s hard-label accuracy, not a semantic-similarity correlation coefficient. These are report results, not an independent Q8_0 benchmark.

More resources

Read the full JJ-1 technical report in English or Japanese for the evaluation setup and detailed results. Register for the JJ-1 inference service.

Inference and licensing

JJ-1 references StartLux-Decision’s inference approach and code. Model weights are licensed under CC BY-NC 4.0; inference code is Apache-2.0. See each model repository for license terms, attribution and usage instructions.