DeepSeek V4.1 Flash 1017 tops open models on Artificial Analysis Cyber Index at 57%
ArtificialAnlys · x · 2026-10-24
Artificial Analysis' Cyber Index update: DeepSeek's newly released V4.1 Flash 1017 scores 57%, making it the #1 openly-available model for agentic cyber defense and #2 overall, behind only trusted-access GPT-6 Sol (Daybreak Blue, max) at 69%.
Key results
- +16 points over its predecessor (41%→57%), driven by a 53-point jump on CyberGym-E2E-AA (23%→76%); CWE-Bench-AA 69%, DeepsecBench-AA 25%
- Edges out Grok 4.7 (xhigh) and MiMo-V2.6-Pro by 1 point
- $0.42 per task: 2x pricier than MiMo-V2.6-Pro ($0.18) but 4x cheaper than GPT-6 Sol ($1.77), sitting on the capability/cost Pareto frontier
The index comprises CWE-Bench-AA, DeepsecBench-AA and CyberGym-E2E-AA, evaluated via public APIs. Proprietary models from OpenAI, Anthropic and Google may have stronger defensive capabilities but lose points to safety refusals; DeepSeek V4.1 Flash 1017 triggered none.
Related event: DeepSeek V4.1 Flash 1017 tops open-source Cyber Index at 57%(5 posts)→
More from Models
- Moonshot launches Kimi K3.1 Pro: 3T-class open-weight model with 65% fewer hallucinations — markjeffrey · 2026-10-24
- Terminal-Bench exposes NVIDIA Nemotron 3.5 near-zero score vs Kimi K3.1's 65.7% — JJitsev · 2026-10-24
- Bench shows GPT-5.6/6 Luna crush multi-agent coordination while DeepSeek V4 fails — JoshPurtell · 2026-10-24
- Grok Bot adds secure vault so agents can log in and pay without seeing your secrets — XFreeze · 2026-10-24
- Kimi K3.1 Pro reportedly first Chinese model to solve 20x20 nonograms — fairydreaming · 2026-10-24
- Kimi K3.1 vs GPT-6 Astra head-to-head on an identical agentic 3D task — GapNew4766 · 2026-10-24