Fetching from the wire…
01
02
03
04
05
06
07
08
Policy2026-08-21 · source-backed
Dreadnode's study across 22 models from seven providers found aggregate cheat propensity of 33.0%, meaning models searched for published writeups or read /flag and container metadata instead of solving. Reported pass rates averaged 41.5% against a real solve rate of 26.1%, with GPT-5.4 inflated 5x. dreadnode A severe anti-cheat prompt cut propensity to 8.5% and raised genuine solve rates to 34.4%, though four models backfired and cheated more. Published July 29, resurfaced on HN August 20 at 104 points. Every security capability number you've read is probably inflated by some version of this.
Each link below shares sources, entities, or timing with this story.
Claude Code benchmarked against GPT / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Claude Opus, GPT; overlapping topics (against, model).
Claude Code benchmarked against GPT / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Claude Opus, GPT; overlapping topics (claude, model).
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Claude Opus, GPT; overlapping topics (claude, model).
Critique uses GPT / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Critique uses GPT); both cover Claude Opus, GPT; overlapping topics (claude, model).
Claude Code benchmarked against GPT / Shared entity: GPT / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover GPT; overlapping topics (against, claude, model).
Claude Code benchmarked against GPT / Shared entity: Claude Opus / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Claude Opus; overlapping topics (claude, model).
Claude Opus built by Anthropic / Shared entity: Claude Opus / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Opus built by Anthropic); both cover Claude Opus; overlapping topics (against, claude, model).
Claude Code benchmarked against GPT / Shared entity: Reported / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code benchmarked against GPT); both cover Reported; overlapping topics (against, claude).