Google unveiled Gemini 4 Carbon, their latest frontier AI model built on Gemini 4 Argon, with state-of-the-art cybersecurity capabilities and sustained agentic workflows that take on harder, long-horizon engineering problems.

Gemini 4 Carbon comes with multimodality and 1M tokens context window, as Google claims it to be their most-capable AI model yet, with gains in coding quality, agentic reliability, scientific tasks, full-stack web development, and multimodal understanding, with the model trained to avoid shortcuts and deliver consistent results on complex assignments.

Gemini 4 Carbon is our next frontier model.

It’s state-of-the-art across cybersecurity and long-horizon capabilities.

— Google DeepMind (@GoogleDeepMind) October 28, 2026

The model posts 88.2 percent on SEC-bench Pro for identifying vulnerabilities, 54.8 percent on ExploitGym for exploitation, and 71.0 percent on CWE-bench for patching; it also advanced 89 Elo points to fourth place at 1768 on WebDev Arena and reached 96.2 percent on the long-context GraphWalks benchmark spanning 256,000 to 1 million tokens.⁠

Gemini 4 Carbon launch comes barely two weeks after Google had rolled Gemini 4 Argon and as per the company, it has been built on the same multi-layered safety and security stack of Argon by “combining model training, real-time misuse defenses, prompt-injection resilience, and chain-of-thought monitoring.

Also Read: Open-Weight, Coding Agents and Battle for Cheaper AI: Model Launches in October 2026

According to Google, Gemini 4 Carbon is available only for limited partners for testing as the company has voluntarily opted for pre-release model testing by the US government.

The company intends to release Gemini 4 Carbon to the public at $2 per million input tokens and $10 per million output tokens, with cached input tokens priced at 95% off input token price.

“We’re continuing to gather feedback and iterate on guardrails before making Carbon available to developers, businesses, and consumers via our product surfaces as soon as possible,” wrote Google in a blogpost on Wednesday.

Artificial Analysis has ranked Gemini 4 Carbon first position on their Intelligence Index v5 and second on coding agent index, trailing only behind Anthropic’s Claude Opus 5.5 model.

Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index

Gemini 4 Carbon scores 59 on Intelligence Index v5, driven by leading performance in complex reasoning, knowledge, and scientific tasks. It also has large gains in coding and knowledge work, particularly when compared to other Gemini models, but it is not leading in all these areas.

As with launch of Gemini 4 Argon, Gemini 4 Carbon is being rolled out to selected users and is not yet publicly available. Google is offering a 50% launch discount, with no confirmed end date. All our charts and figures use standard pricing for both Gemini 4 Carbon and Argon.

Key results for Gemini 4 Carbon with high reasoning:
➤ Gemini 4 Carbon leads the Intelligence Index v5, with the #1 score in 4 of the 9 Index evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, AutomationBench-AA. Carbon makes substantial gains elsewhere but is not leading in coding and knowledge work

➤ Behind only Claude Opus 5.5 on coding agents: With Antigravity CLI, Gemini 4 Carbon (high) scores 59 only 3 points behind Claude Code with Claude Opus 5.5 (max, 62) on the Artificial Analysis Coding Agent Index. Carbon ranks second on both Terminal-Bench 4.0 (64%) and FrontierCode v1.1 (51%), behind Claude Opus 5.5 (max) at 56%. Google has historically underperformed in this area and so this improvement stands out

➤ Improved agentic knowledge work, but not yet leading: On AA-Briefcase, Gemini 4 Carbon (high) scores 1609 Elo, a 126-point improvement over Gemini 4 Argon (high, 1483), but still behind models including Grok 4.7 (xhigh, 1638), Muse Wonder (max, 1659) and Kimi K3.1 Pro (1678). The largest gain comes from Presentation, up 293 Elo to 1598, alongside a 120-point improvement in Analytical Quality to 1671

➤ Lower Cost per Task than Claude Opus 5.5 for comparable overall intelligence: Gemini 4 Carbon costs $7.76 per Intelligence Index task, ~23% less than Claude Opus 5.5 (max, $10.04) but ~1.2x GPT-6 Astra (max, $6.25). It uses 123k output tokens per task, 29% fewer than Claude Opus 5.5 (max, 173k). At the same $4/$20 standard pricing, its Cost per Task is in line with Gemini 4 Argon ($7.68), while scoring 9 points higher on the Intelligence Index

➤ Leading AA-Omniscience v1.1 score, with low hallucination: Gemini 4 Carbon scores 54 on our recently updated AA-Omniscience v1.1, 6 points ahead of Claude Opus 5.5 (max, 48) and 8 points ahead of Gemini 4 Argon (46). Accuracy (% correct) rises 10 points over Argon to 58%, while its hallucination rate rises from 4% to 11%. This is still the second lowest of any model, behind only Argon, compared with 50% for both Claude Opus 5.5 (max) and GPT-6 Astra (max)

Key model details:
➤ Context Window: 1M tokens
➤ Multimodality: Text, image, video, and speech input, with text output
➤ Pricing: $4/$20 per 1M input/output tokens, the same as Gemini 4 Argon’s standard pricing, with a 50% discount. Cached input tokens receive a 95% discount ($0.20 per 1M)

Congratulations to the @GoogleDeepMind team!

— Artificial Analysis (@ArtificialAnlys) October 28, 2026

“Internally, our teams have seen Carbon run for days to persist through dead ends to tackle complex, multi-step engineering tasks like root-causing and patching subtle bugs across large codebases and low-level systems..On internal benchmarks, Carbon achieves more than 2x uplift in success rate for generating secure code over Argon,” wrote Google.

Artificial Analysis also noted while Gemini 4 Carbon shows improved agentic knowledge work that Gemini 4 Argon, it still trails behind Grok 4.7 (xhigh, 1638), Muse Wonder (max, 1659) and Kimi K3.1 Pro (1678).

Meanwhile, Arena AI reported that Google DeepMind’s Gemini 4 Carbon has claimed the top spot in its Text Arena and second place in the Agent Arena, while ranking fourth in the Code Arena for WebDev. According to the platform’s community evaluations, the model posted a 16.2 percent net improvement across more than 21,900 real-world agentic sessions and delivered results at a median cost 72 percent below the leading Claude Opus 5.5.

Exciting news: Gemini 4 Carbon (High) from @GoogleDeepMind just made a huge debut on Arena, landing #1 in Text Arena, #2 in Agent Arena, and #4 in Code Arena: WebDev. Back at the top, Gemini 4 Carbon delivers frontier intelligence and reshapes the Pareto frontier across three arenas.

In Agent Arena, Gemini 4 Carbon ranks #2 with a +16.2% net improvement across +21.9K real-world agentic sessions from our global community, surpassing top models GPT-6 Astra and Fable-5.1. At $1.80 median cost per task, Gemini 4 Carbon (High) costs 72% less than the #1 ranked Claude Opus 5.5 (Max).

Its standouts by key signals:
– #1 Steerability (+18.6%): can the model course-correct when you push back?
– #2 Praise vs Complaint (+37.9%): implicit sentiment in users’ reactions
– #3 Confirmed Success (+18.7%): explicit “yes, that worked” from users

In Code Arena: WebDev, Carbon scored 1768 pts landing #4:
– Just 2 pts below #3 Claude Sonnet 5.5 (xHigh), at 1770 pts
– 89 pts above #11 Gemini 4 Argon (High), at 1679 pts

By category, it ranks #3 in Gaming and Simulations, and #5 in Brand & Marketing.

In Text Arena, Gemini 4 Carbon (High) is the new #1 with 1528 pts, now ahead of Gemini 4 Argon (High) at #2 with 1520 pts.

Congrats to the @GoogleDeepMind team on this huge milestone!

— Arena.ai (@arena) October 28, 2026

Arena further cites leading marks in steerability, positive user sentiment, and confirmed task success, concluding that Gemini 4 Carbon has reshaped the Pareto frontier across its text, agent, and coding benchmarks.

Also Read: Google Unveils Gemini 4 Argon for Coding, Research and Cybersecurity