Google's strongest model, announced October 28 (Pacific time): first on AA v5.0 at 59 (high), officially positioned for cybersecurity and long-horizon work. SEC-bench Pro 88.2%, ExploitGym 54.8% and CWE-bench 71.0% are vendor figures, with external benchmarks noted as unguarded. Access opens this week to cyber defenders; developers and consumers wait. Introductory pricing is $2/$10 per million tokens, later $4/$20.
From October 29, 2026 this board reads Artificial Analysis Intelligence Index v5.0 in full (the methodology page names v5.0 the same day): GDPval-AA exits, FrontierCode 2.0 (132 tasks from real open-source repositories, scored by maintainers' willingness to merge, blocking check failures score zero) weighs 15%, Terminal-Bench 4.0 weighs 10%, and knowledge work / coding / science / general each weigh 25%, with several evaluations on private data. Each model still uses its highest tested setting with fallback conditions retained; v5.0 and v4.3.2 scores cannot be compared across versions. Kimi K3, GLM-5.3-Flash, Qwen3.8-Flash-Next and Nemotron 3.5 Bolt 74B-A9B have no scored row on the v5.0 source table and leave the board (their last v4.3.2 values 44/42/40/21 remain in records); GPT-6.1 Terra now appears on the source table and joins under this board's rules; Gemini 4 Carbon (announced October 28) leads at 59 (high) without general availability yet. For Grok 4.7 under v5.0, high (35) outranks xhigh (34), so high is taken. Compare within one evaluator and one version; the index mainly measures English text tasks — judge Chinese and image capabilities separately.
Google announced Gemini 4 Carbon on October 28 (Pacific time): on Artificial Analysis's new Intelligence Index v5.0 it ranks first at 59 (high effort).
Independent evaluation · full-board reread October 29, 2026
Flash advances coding, multi-step reasoning and agent work at the same speed and price positioning; Flash Cyber is a separate security-focused variant.
The same model expands to the paid API, Gemini Pro/Ultra and development tools; shared context and long-decode conditions matter. Copilot has separate plans and gradual rollout.
A new generation of the real-time interactive world model: native audio, on-the-fly text steering and Gemini-planned multi-step events; a research preview reaches trusted testers first, then Project Genie for AI Ultra in coming weeks. No board entries — the scope gap stays stated.
A new frontier model: first on AA v5.0 at 59 (high), officially positioned for cybersecurity and long-horizon work. Access reaches a small group of cyber defenders this week, widens via Fairwind, and stays pending for developers and consumers; introductory pricing is $2/$10 per million tokens, later $4/$20. A high score is not general availability.