Mistral Large 4 solves 18 of 19 CTF challenges in official speedrun with tool calls
MistralAI · x · 2026-10-07
Mistral published a cybersecurity speedrun for Mistral Large 4: the model worked through 19 CTF challenges with tool calls, with solve times grounded in actual runs, and solved 18 of them. The company pitches it as one of the world's strongest models for security work, emphasizing efficient reasoning over diverse complex tasks.
More from Models
- "Astra Pause Syndrome": steering may be making models go silent, OpenAI has a workaround — thursdai_pod · 2026-10-07
- Unverified rumor suggests Qwen4 Flash is a 400B parameter model, comparable to GLM 5.3 Flash — EAccelerate_42 · 2026-10-07
- Anthropic Expands Cyber Verification Program With Three Tiers, Opens Door to Authorized Offensive Work — EricBuess · 2026-10-07
- Mistral Large 4.0 weights reportedly landing at end of October — cpldcpu · 2026-10-07
- Claude's "reasoning extraction" guardrail blocks users from seeing its thinking, and they're not happy — StewartalsopIII · 2026-10-07
- Grok's quirk: it says 'No.' then argues your point better than you did — gandamu_ml · 2026-10-07