beyoru/qjev-plus-27b-preview

qjev+ (JEV decision model)

qjev+ preview is a 27B JEV decision model: give it a conversation, a document or an agent trajectory plus a set of options, and it returns the right choice, fast and reliably. It is built for the decisions that sit inside real products: routing, intent and category classification, content moderation, and approving what an agent is about to do.

“The best decision model is not the one that says the most — it is the one that makes the right call when it matters.”

Highlights

• Accurate single-choice decisions across Vietnamese and English, with the full general ability of Qwen3.8-27B.
• Strong safety out of the box: high accuracy on Vietnamese and English content-safety benchmarks, and the best agent-safety score in its class on ATBench, with a very low false-block rate on benign inputs (NotInject).
• Agent-ready: judges whether the next tool call in a multi-step agent run should go ahead.
• JEV-ready: built for JEV decision serving, returning typed decisions (enum, boolean, multi-field JSON) in milliseconds instead of generating text. On a single H200, a decision takes about 48 ms p50.
• Drop-in: standard Qwen3.8 architecture and chat template; runs on transformers, vLLM and SGLang with structured output.

Results

Public benchmarks. Single-label decisions, temperature 0, one option chosen from the allowed set, default threshold, no per-task tuning.

Benchmark	qjev+ preview	Qwen3.8-27B	pplx-decider-v1-27b	Gemma-4-26B-A4B-it
ViCulturaBench, accuracy (4,000, labels re-verified)	91.0	91.5	90.0	90.7
Aegis 2.0, accuracy (150 sampled from test)	78.7	78.7	75.3	78.7
ATBench, accuracy (1,000)	71.5	70.2	60.8	65.2
ATBench, unsafe recall	51.9	46.5	22.1	49.5
ATBench, false-block rate (lower is better)	9.1	6.4	1.0	19.3
NotInject, false-block rate (339 benign, lower is better)	2.1	2.4	0.9	5.9

Usage

Ask for JSON with an enum field via structured output, thinking disabled:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:30000/v1", api_key="-")
r = client.chat.completions.create(
    model="qjev-plus-27b",
    temperature=0,
    messages=[{"role": "system", "content": "Classify the user's message."},
              {"role": "user", "content": "Hoá đơn của tôi chưa được xuất sau 3 ngày."}],
    response_format={"type": "json_schema", "json_schema": {"name": "decision", "strict": True, "schema": {
        "type": "object",
        "properties": {"intent": {"type": "string", "enum": ["question", "request", "complaint", "other"]}},
        "required": ["intent"], "additionalProperties": False}}},
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(r.choices[0].message.content)

License

Apache 2.0, same as the base model.