DeepSeek V4.1 Flash 1017 takes #1 open-model spot on Cyber Index, CyberGym up 53 points
ArtificialAnlys · x · 2026-10-24
DeepSeek's V4.1 Flash 1017, an update to its flagship open-weights model, jumps 16 points on the Artificial Analysis Cyber Index (41%→57%), becoming the #1 openly-available model — ahead of Grok 4.7 (Xhigh) and MiMo-V2.6-Pro at 56.
- The gain is driven by a 53-point leap on CyberGym-E2E-AA end-to-end vulnerability discovery and patching (23%→76%)
- The index combines CWE-Bench-AA, DeepsecBench-AA, and CyberGym-E2E-AA evaluations on finding, reproducing, and patching real vulnerabilities
- Some restricted-access proprietary models may score higher on cyber defense, but DeepSeek 1017 is the new leader among openly available models
More from Models
- LiveBench creator to evaluate Kimi K3.1, betting his benchmark can't be gamed — bindureddy · 2026-10-24
- Kimi K3.1 Pro tops SWE Marathon and agent benchmarks, fueling open-source 'last time they catch up' debate — cephaloform · 2026-10-24
- Kimi K3.1 Pro tops Humanity's Last Exam with tools at 70.0, ahead of Opus 5.5 — UltraRareAF · 2026-10-24
- Peter Gostev demos 3D generation with Kimi K3.1 Pro — arena · 2026-10-24
- Kimi K3.1 Pro hits #4 lab on Code Arena WebDev, 74% cheaper than Claude Opus 5 — arena · 2026-10-24
- Moonshot Kimi now ranks #4 lab on Code Arena WebDev leaderboard — arena · 2026-10-24