Expired50% confidenceBenchmarkExact time
Mistral Large 4 scores 93% on the cybersecurity benchmark Cybench (40 CTF challenges), 82% on vulnerability reproduction and patching tests, and 93.3% on the B3 AI security benchmark.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/26/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn a capture-the-flag speedrun test, Mistral Large 4 completed 18 out of 19 security challenges, outperforming Opus 5.5 and GPT-6 Astra in cybersecurity, partly because approximately 40% of tasks were blocked by safety filters in the latter two.74% similarUnverifiedMistral Large 4 scored approximately 62% on the real-world software engineering benchmark DeepSwee.72% similarUnverifiedIndependent testing shows Mistral Large 4 achieved a success rate of 81.7% on the CyberGym E2E end-to-end test, the highest among 18 tested models.70% similarUnverifiedMistral Large 4 solved 18 out of 19 capture-the-flag (CTF) challenges, and in a malware reverse-engineering test identified Cobalt Strike, extracted configurations and indicators of compromise, and generated an investigation report containing Yara rules within 12 minutes.69% similarUnverifiedMistral Large 4 achieved 61.7% on SWE Atlas Q&A, 28.3% on Terminal Bench, and 49.8% on the综合 Coding Agent Index.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007328API
curl https://kongchang.com/api/v1/knowledge/claims/1007328MCP
get_claim(id=1007328)