DEV Community

Cover image for ZDNet Korea: VIDRAFT's 180B Darwin Outscores a 2.8 Trillion Parameter Model in Math and Science Reasoning
AI OpenFree
AI OpenFree

Posted on Originally published at vidraft-ai-media.static.hf.space

ZDNet Korea: VIDRAFT's 180B Darwin Outscores a 2.8 Trillion Parameter Model in Math and Science Reasoning

TL;DR

On November 17, 2026, ZDNet Korea, one of Korea's main technology news outlets, reported that VIDRAFT's large language model Darwin-180B-RSI ranked first among open-weight models in the mathematical and scientific reasoning track of SuperCLUE's November 2026 evaluation.

The headline of the article is the size gap. Darwin has 180 billion parameters. Moonshot AI's Kimi K3.1 Pro has 2.8 trillion, about 16 times more. Darwin scored more than 10 points higher. Including closed models, Darwin placed second, directly behind OpenAI's GPT-6.1 Sol.

SuperCLUE November 2026 math and science reasoning results

What ZDNet Korea reported

Point What the article says
Result First among open-weight models and second overall in math and science reasoning
Size A 180 billion parameter model scoring more than 10 points above a 2.8 trillion parameter model
Model synthesis VIDRAFT analyzes the feed-forward network regions where knowledge is concentrated in two or more open models, extracts the strengths of each and synthesizes them into one model
Self-improvement The synthesized model generates its own solutions, checks the answers automatically and retrains only on the correct ones. No human-written solutions or reasoning traces are used
Hugging Face records Number one in 12 benchmark leaderboards, GPQA 94.44, full marks on AIME 2026 and HMMT
Inference speed 18,057 tokens per second on server GPUs and 417 tokens per second on an NPU
On-device POCKET, the light edition, runs on a single laptop
Downloads About 5 million cumulative downloads on Hugging Face, more than 1.2 million a month, and 1.19 million for POCKET in the last 30 days
National project VIDRAFT is a consortium member of the government's security foundation model development project led by Naver Cloud, in charge of AI model safety diagnosis and risk response

The article closes with a comment from CEO Kim Minsik: self-improvement, where the model writes problems, verifies them and corrects its own weights, together with synthesis that takes only the strengths of parent models, opened the way for a small model to beat a giant one.

Two technologies behind the result

Model synthesis. Darwin starts from open models that are each strong in a different area. VIDRAFT finds where each parent stores its knowledge and builds one child model that carries those strengths together.

Model-level recursive self-improvement (RSI). The child model then improves itself. It solves problems, an automatic checker confirms which answers are right, and only verified solutions go back into training. The loop runs again on the improved model. The improvement is in the weights themselves.

The numbers

Mathematical and scientific reasoning, SuperCLUE November 2026:

Rank Model Developer Open weights Score
1 GPT-6.1-Sol OpenAI No 76.32
2 Darwin-180B-RSI-R3 VIDRAFT Yes 73.68
3 Gemini-4-Argon Google No 71.05
3 DeepSeek-V4.1-Flash DeepSeek Yes 71.05
5 Grok-4.7 xAI No 68.42

SuperCLUE grades each model itself every month on private questions. Developers do not submit scores.

A run of coverage

ZDNet Korea's report follows The Korea Economic Daily on November 16 and Seoul Shinmun on November 13. ZDNet Korea has covered VIDRAFT steadily this autumn: the 10 number-one records on Hugging Face (October 6), NPU training acceleration (October 13), pretraining on NPUs alone (October 14) and the in-model security technology that blocks information leaks (November 3).

Links

FAQ

Which open-weight model is first in SuperCLUE math and science reasoning?

In the November 2026 evaluation, Darwin-180B-RSI from VIDRAFT is first among open-weight models with 73.68 points and second overall.

How can a 180B model beat a 2.8T model?

VIDRAFT combines two methods: synthesis of the strengths of several parent models, and recursive self-improvement on self-generated, automatically verified solutions.

Can Darwin run on a laptop?

Yes. POCKET, the light edition, runs on a single laptop and was downloaded 1.19 million times in the last 30 days.

Top comments (0)