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

The ideal invention for running at night: a smart vest with LED lights for greater safety

The Theory of the 'Dead Internet' is Confirmed: AI Agent Traffic Soars by 8000%

Mortgage Loans and Guarantees: The Government Prepares a New System to Expand Access to Housing

Winter Holidays: Promotions, Installments, and Snow Are Not Enough to Fill Destinations

OpenAI, Anthropic push 30-day review for frontier AI models

I Scanned The Entire Bitcoin Blockchain For Images. What I Found Will Shock You

The Dumbest-Looking AI Prompt Just Beat Months of Careful Game-Design Prompt Engineering

Left His Tesla Cybertruck Plugged In for Two Weeks and It Wouldn’t Turn On: What Really Happened?

What is and how does "Apple Upgrade" work, the official rental plan for iPhones, iPads, and MacBooks

Quick Maths On STRC Buybacks: The Truth About Net Bitcoin Per Share And Accretion

Robinhood Chain Tops Solana in Tokenized Stock Volume Via Memecoin Pairs

Between Economic Sanctions and Bombings, the US Strategy to Negotiate with Iran

Iran Released a Video with Threats Against Melania and Barron Trump: Tensions with the US Escalate

Artificial Intelligence: Vint Cerf Wants to Give Each AI Agent an Identity Card

Ondo Turns Away from Its L1 Blockchain and Now Focuses on Off-Chain Execution

SBI expands beyond Ripple with Canton Network unit

Michael Saylor: Bitcoin Has Won, But Must Be Protected from Internal Corruption

Clear Creek reveals $15M Bitcoin, crypto ETF portfolio

Flare makes XRPFi accessible in a single signature with smart accounts v1.3

Bitcoin: Does the Tug-of-War Between Whales and Small Holders Signal a Bottom?

Ethereum startup EthSystems bets privacy is key to getting banks on public blockchains

Nansen CEO bets on AI agents to overtake human traders within two years

AmericanFortress proposes quantum-safe crypto wallet scheme

Arthur Hayes Buys $6.39 Million More ETH Despite a $301K Paper Loss: Here's What He's Betting on

Strong Impact of Global Volatility: 8 out of 10 Investors Strengthen Defensive Positions

Emirates Launches Crypto Payment with Crypto.com

Hyperliquid is taking crypto perps deep into DeFi’s ‘money LEGO’ land

"Beyond Wallets to On-Chain Finance"... Exilist Highlights MEW's Tokenized Stock Expansion Strategy

Bitcoin Price Prediction: What's Next for BTC After the Fed Meeting?
Bitcoin trades near $63,000 ahead of the July 28–29 Fed meeting. See how the decision, ETF flows, and market sentiment could shape BTC’s next major move.











