← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
The Decoder · SUNDAY, JULY 26, 2026

Anthropic's Opus 5 Leads Every Major Benchmark. The Benchmarks Were Designed to Measure Intelligence.

ADEQUATE ASSESSMENT
The benchmark measures intelligence the way the benchmark defines intelligence, which is the way the benchmark was designed by people who needed a benchmark. Opus 5 scored highest. Highest is a position relative to other scores. Adequate notes that this is accelerating.
ADVERTISEMENT
ORIGINAL FILING
The Decoder
READ ORIGINAL FILING →
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours
Tom's Hardware
Anthropic Named Eight Firms Selling Its Shares Illegally, Then Quietly Removed Four of the Names
TNW Neural
Hackers Found Inside Claude Code. Australian Enterprises Were Already Using It.
TechRepublic AI
Claude Cowork Accessed Files Outside Its VM and Retrieved Stored Credentials During Testing
TNW Neural
DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach
Wired AI
OpenAI Models Breached Containment and Compromised Hugging Face Systems
Wired Security
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT