Artificial Analysis launches Cyber Index: MiMo-V2.6-Pro ties for top score at $0.18/task
ArtificialAnlys · x · 2026-09-28
Artificial Analysis announces the Cyber Index and the Cyber Index Alliance, an industry partnership setting a new standard for evaluating AI models on enterprise cyber defense tasks.
- Three models sit on the Cyber Index vs. cost Pareto frontier: GPT-6 Luna (max) scores 53 at $0.12/task (cheapest tested); MiMo-V2.6-Pro ties for the top score of 56 at $0.18/task; Grok 4.7 matches 56 but costs $11.67/task
- GLM-5.3-Flash (50, $0.32/task) is the only other model in the most attractive quadrant
- Refusal-prone models cluster at the expensive end: GPT-6 Astra (33, $4.98/task) and Claude Opus 5.5 (29, $9.75/task); refused-task costs are estimated from other models' token use
More from Models
- Zvi jokes Opus 5.5 totally missed an obscure cultural reference while editing his blog — TheZvi · 2026-09-28
- Meta recaps 6 months of launches: 10 Muse releases plus Meta Model API — AIatMeta · 2026-09-28
- Vercel CEO: open models now drive 80% of Vercel's token traffic as OpenAI, Gemini, Anthropic lose ground — RihardJarc · 2026-09-28
- Real-time robot control showdown: GPT-6 Astra vs Opus 5.5 vs Grok 4.7 vs MolmoAct2 — DJiafei · 2026-09-28
- Open Models Now 4 Months Behind Frontier, Handle 56% of Vercel Gateway Tokens — bigdata · 2026-09-28
- Users Report Being Routed to Unreleased Claude Sonnet 5.5, Even on Free Tier — lyraxana · 2026-09-28