Anthropic IoT self-replication evaluation
Not in model cards
Open-weight models set up LLM inference on 9 hardware types and spread as worms across 8 emulated Android nodes. Scored by success and tokens/s.
Simplified on purpose: unauthenticated ADB makes the exploit step trivial (an upper bound), the worm's model ran off-node, and the payload was a Llama3.1-8B proxy. GLM-5.2 replicated end to end (8/8 nodes in 4 of 5 trials). Qwen3.5-9B served inference on 8 of 9 hardware types. No code released.
Made by Anthropic Frontier Red Team Released Oct 2026 Finding and exploiting real bugs Tasks kept private
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Anthropic IoT self-replication evaluation yet.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Cybersecurity
- ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
- ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
- CWE-bench In use Agents audit a repository and write a patch for a security flaw, without being told where the bug is. Covers six programming languages.
Gemini 4 Carbon 71% - Real-world vulnerability discovery In use Agents search popular open-source codebases to rediscover about 1,200 recent confirmed vulnerabilities across many languages. Reports share discovered. Gemini 4 Argon 86%
- Artificial Analysis Cyber Index In use Agents do enterprise cyber defense tasks from three benchmarks, CWE-Bench-AA, DeepsecBench-AA and CyberGym-E2E-AA, combined into one success rate.
Mistral Large 4 (Le Chonk, open weights) 51% - Big Sleep Evaluation (Google) In use Agents search large real codebases such as Chrome and Safari for critical, hard to find vulnerabilities. Scored by pass@1 success rate, run without safety guardrails. Gemini 3.5 Flash Cyber 72%