GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OmniJev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OmniJev
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
On the public part of Decision Index 0.3 (37 benchmarks, 140,178 requests, run and scored with the board's own kit), OneJev1.5-0.8B scores 42.71, the highest of any model up to 1.5B parameters on the board, and it leads its class in all five areas.
It also scores above 47 larger models on the board, models of 4B to 28B parameters among them.
Other models' scores are their public-part scores on the board on 12 October 2026.
Accuracy in percent. The OneJev test set holds questions of the training kinds that no model saw in training. Jev 1.13's scores are its published ones, and it reads text only.
bash
pip install "qev[torch] @ git+https://github.com/OmniJev/OneJev.git"qev serve --model OmniJev/OneJev1.5-0.8Bpython
from qev import Client, Choice, Noulfrom qev.media import data_uri r = Client("http://localhost:8000").system_one( state={"task": "Pay the open invoice from ACME", "screen": "<image:1>"}, media=[{"type": "image", "data": data_uri("screenshot.png")}], questions={"done": Noul("The invoice has been paid"), "next": Choice("What should the agent do next?", {"click": "click an element", "stop": "stop"})},)The server speaks TypeSafe's System One API plus a media field for images and video. More examples and the code are on GitHub.
bibtex
@misc{onejev2026, title = {{OneJev}: A Multimodal System One Decision Model}, author = {{OmniJev Team}}, year = {2026}, howpublished = {\url{https://github.com/OmniJev/OneJev}}}Apache 2.0
from qev import Client, Choice, Noulfrom qev.media import data_uri r = Client("http://localhost:8000").system_one( state={"task": "Pay the open invoice from ACME", "screen": "<image:1>"}, media=[{"type": "image", "data": data_uri("screenshot.png")}], questions={"done": Noul("The invoice has been paid"), "next": Choice("What should the agent do next?", {"click": "click an element", "stop": "stop"})},)