Microsoft Says MDASH Beats Claude Mythos and GPT-5.6 Sol in Cybersecurity Test
Microsoft has released its first dedicated cybersecurity model named MAI-Cyber-1-Flash and plugged it into MDASH, a vulnerability-hunting system that it says beats Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol while costing 50% less than Microsoft's current best MDASH configuration, according to the company.
The combined setup scored 95.95% on CyberGym, according to Microsoft. CyberGym is a benchmark that asks AI agents to reproduce 1,507 known vulnerabilities across 188 open-source projects, then scores them by the percentage successfully reproduced in a controlled environment.
That put MDASH ahead of GPT-5.5 Cyber at 85.6%, Mythos 5 at 83.8%, GPT-5.6 Sol at 83.6%, and Gemini 3.5 Flash Cyber at 83.2%. The result is self-reported by Microsoft and had not appeared on CyberGym's public leaderboard at publication time, though the benchmark uses a public test set and a defined success metric.
MAI-Cyber-1-Flash does not work alone. Microsoft says it handles up to 90% of tasks, while MDASH routes the hardest 10% to GPT-5.4. That matters because tokens---the chunks of text an AI processes---cost money every time a model reads code or produces an answer.
This is the first time a Microsoft model built for efficiency is capable of beating a dense state of the art model built with general capabilities in mind. "When combined with MDASH, (MAI-Cyber-1-Flash) delivers world-class performance at 50 percent of the cost of leading models," Microsoft CEO Satya Nadella wrote.
A model (in this case MAI-Cyber-1-Flash) is the AI that reasons over the code. A harness (MDASH in this case) is the machinery around it: the agents, tools, checks, and workflow that decide where to look, challenge suspected findings, remove duplicates, and prove that a bug can be triggered.
MDASH uses more than 100 specialized agents assigned to audit code, debate whether a finding is genuine, and build a proof of concept---a working demonstration that the flaw exists.
Microsoft said occasional scans and delayed patches are becoming obsolete as AI makes bug discovery cheaper. The company argues that decades of security data give it an advantage, adding, "No one can manufacture this history."
Ever since the release of Claude Mythos, cybersecurity experts have been trying to beat or match its capabilities. Researchers reproduced Mythos-style vulnerability hunting with public models for under $30 per scan. Dawid Moczadło, one of the researchers involved, said "the moat is moving from model access to validation."
The scarce part is becoming the system that proves findings without burying developers under false alarms.
Decrypt also reported that GPT-5.5 Cyber had recently taken the public CyberGym lead with an 85.6% score, narrowly beating Mythos. Microsoft's score is about 10 points above GPT-5.5 Cyber and 7.5 points above MDASH's previous result, but it evaluates the full system rather than MAI-Cyber-1-Flash by itself.
Microsoft is putting MDASH into private preview through Microsoft Security Exposure Management in the Defender portal. Customers can scan Git repositories, see findings ranked from unlikely to proven, and use the Defender CLI to generate proposed code fixes for developer review.
The preview currently limits repositories to roughly 256MB and permits one concurrent scan per tenant. Project Perception is expected to extend the same multi-agent approach beyond code scanning into broader threat monitoring and remediation workflows.
This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.
You may also like

Cryptocurrency Market in Russia to Receive General Rules and a Register of Digital Depositories

SEC keeps Nasdaq bitcoin options on hold after granting CME review

The Self-Proclaimed Satoshi Nakamoto Attacks Bitcoin Governance Model

XRP extends the longest active ETF inflow streak in crypto as rival funds struggle for fresh cash

Hank Green and the AI Addiction: The Warning Creators Ignore

Counting down the days: State of Crypto

Dibu Martínez's Future Takes a Turn After Key Decision by Aston Villa: Is He Staying?

Post-Quantum Security: AI Discovers Vulnerability in One of the Candidates for New Digital Signatures

Eight Years of Bitcoin Savings Lost in Fifteen Minutes. Hardware Manufacturer's Error Cost 1367 BTC

Due to the income and salary crisis, 62% of Argentines have gone into debt to cover basic expenses

18 Million Dollars in 42 Days: The Sale That Funded Ethereum – The Crazy Crypto Stories

Iguazu Falls: Devil's Throat Closed for 40 Days Due to Possible Flooding

Casemiro's Forgettable Night at Inter Miami: Two Mistakes and an Own Goal in Lionel Messi's Return to MLS

BCRA Reform: Broad Support for Emission Limits and Some Reservations on the Single Mandate

Trump’s legal loophole around the Supreme Court is keeping inflation alive – and trapping Bitcoin in the Fed’s crosshairs

Are stablecoins really fee-free?

What Does Waller Think? Will There Be a Rate Hike in September? Markets Are in a Dilemma Ahead of the August Jackson Hole Meeting

Crypto Exchange Binance Faces New Revelations on Transfers Linked to Iran

The reverse bridge: Crypto meets Wall Street using perps

Tesouro IPCA+ Drives Record for Tesouro Direto in June

OPEC+ Increases Production by 188,000 Barrels: What Changes in Oil

South Korea's 22% Cryptocurrency Tax to Take Effect in 2027! Opposition Voices: Losses Cannot Be Offset, Risking Trader Exodus

Court Denies xAI's Request to Block First AI Service Ban in the US for 'Undressing' People

IPS Discounts: All the Tourist Benefits for Retirees and Pensioners

BNB Chain sues ex-employee over $628K memecoin trade

The sudden collapse of a $20 billion AI fund reveals why Bitcoin is the first thing Wall Street sells when margin calls hit

Privacy in Chromia: Are AI agents truly free from surveillance?

Crypto Traders Find New Meme Coin: Now They Bet on AI and Semiconductors

Donald Trump releases the $1.2 million data feed that lets Wall Street front-run his market-moving policy announcements











