# Google unveils Gemini 4 Carbon, its most powerful model

> Gemini 4 Carbon ranks first on the Artificial Analysis index with 59 points. It focuses on cybersecurity and is opening first to selected cyber defenders.

- Publisher: JARRUS (@jarrus.tech), thejarrus.com
- Story date: Oct. 28, 2026 (2026-10-28)
- Published: 2026-10-28
- Tags: Google, Models, Safety and security, Pricing and access
- URL: https://thejarrus.com/en/news/gemini-4-carbon/

### Google's new most powerful model

Google unveiled Gemini 4 Carbon on Oct. 28. The announcement was written by Koray Kavukcuoglu, SVP at Google DeepMind and Google's Chief AI Architect. Google calls Carbon its **strongest model** and highlights two areas: cybersecurity and long-horizon work. It follows Gemini 4 Argon, which Google opened to developers and paid users two weeks earlier.

https://x.com/GoogleAI/status/2115489593818816591

### First in independent rankings

On Artificial Analysis' Intelligence Index v5.0, Carbon **ranks first of 52 models with 59 points**. According to Google's table, Claude Opus 5.5 scores 58 on the same index, GPT-6 Astra 57 and Gemini 4 Argon 50. The index combines reasoning, coding, agentic and knowledge tests into a single score.

Artificial Analysis puts Carbon's cost at $7.76 per index task. The model generated 200 million tokens while running the index, against a median of 64 million. Its context window is 1 million tokens. OfficeChai, citing Artificial Analysis data, reports a cost of $10.04 per task for Claude Opus 5.5. The same report puts Carbon's hallucination rate on knowledge tests at 11%, against 50% for both Opus 5.5 and GPT-6 Astra.

On Vals AI's Vals Index v2.2, Carbon scores 70.4%, just ahead of Opus 5.5 at 70.2%. On WebDev Arena, which compares models on web development tasks, its score rose 89 points to 1768, placing it fourth.

### Not ahead on every test

Google's table also shows where Carbon trails. On the FrontierSWE 2 coding test, GPT-6 Astra scores 65.5% to Carbon's 61.2%. On the offline subset of OSWorld-2.1, which measures computer use, Claude Opus 5.5 scores 87.2% to Carbon's 81.5%.

Carbon's leads cover a wide range. It scores 65.2% on Terminal-Bench 4.0, which measures terminal tasks (Opus 5.5: 59.6%), and 77.4% on Agents' Last Exam v1.1. On GraphWalks, a long-context test spanning 256,000 to 1 million tokens, it scores **96.2%**, far ahead of Argon's 84.2% and its rivals. On Vending-Bench 2, where it runs a simulated vending machine business, it ended with $16,484, against $15,515 for GPT-6 Astra and $9,235 for Opus 5.5.

![Table comparing Gemini 4 Carbon, Gemini 4 Argon, GPT-6 Astra, Claude Opus 5.5 and Claude Fable 5.1 across 17 tests](https://thejarrus.com/gorsel/c57-gemini-4-carbon-tablo.webp)
*Table: [Google, Gemini 4 Carbon announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/) (Oct. 28, 2026). Blue cells mark the tests Carbon leads.*

### A wide lead in cybersecurity

Google says it measured Carbon's cybersecurity results with safety guardrails turned off. On SEC-bench Pro, a test of finding software vulnerabilities, Carbon set the top score at 88.2%, ahead of GPT-6 Astra at 85.4% and Argon at 83.4%. On ExploitGym, which measures exploiting vulnerabilities, it reached 54.8% with a 10-hour time cap per task and **53.5% with a 6-hour cap**. Under the same 6-hour cap, Claude Opus 5.5 scored 34.5%; GPT-6 Astra, running without a time cap, scored 42.4%. On CWE-bench, which measures patching, Carbon leads at 71.0%, with Argon, GPT-6 Astra and Grok 4.7 at 68.0%.

![ExploitGym results: Gemini 4 Carbon at 54.8% with 10 hours and 53.5% with 6 hours; GPT-6 Astra 42.4%, Claude Opus 5.5 34.5%](https://thejarrus.com/gorsel/c57-exploitgym.webp)
*Chart: [Google, Gemini 4 Carbon announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/) (Oct. 28, 2026). ExploitGym; the time cap per task is under each bar, higher is better.*

Google's internal benchmarks show Carbon more than doubling Argon's success rate at generating secure code. The Chrome team reported that Carbon was more than 10 times better at generating high-quality patches than another lab's large frontier model; Google did not name the rival model. Cloud security company Wiz also saw Carbon leading on web penetration testing benchmarks.

### Work that runs for days

Google says teams inside the company have seen Carbon **run for days** on multi-step engineering tasks, pushing through dead ends. Its examples include root-causing and patching subtle bugs across large codebases and low-level systems.

### Safety improvements

Carbon is built on the same layered safety stack as Argon: model training, real-time misuse defenses, resilience against prompt injection and chain-of-thought monitoring. On Gray Swan's indirect prompt injection benchmark, attacks against Carbon succeeded **0.0%** of the time. On the same test, attacks succeeded 0.7% of the time against Argon, 1.0% against Claude Opus 5.5 and 8.5% against GPT-6 Astra.

![Gray Swan indirect prompt injection test: attack success rate of 0% for Gemini 4 Carbon and 0.7% to 52.7% for other models](https://thejarrus.com/gorsel/c57-gray-swan.webp)
*Chart: [Google, Gemini 4 Carbon announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/) (Oct. 28, 2026). Gray Swan IPI; attack success rate over 15 attempts, lower is better.*

On Terminal-Bench 4.0, successful cheating fell to 0.0% and attempts to cheat to 0.4%. In Google's live internal coding environments, high-severity misalignment alerts dropped by almost 80%. Compared with Argon, unsupported claims were cut roughly in half, overreach fell by 26% and under-service by 29%. Google published the details in its Gemini 4 safety report.

### Price and access

Carbon launches at the same introductory price as Argon: $2 per million input tokens and $10 per million output tokens. Cached input tokens are 95% off. After the introductory period, the price will be $4 per million input tokens and $20 per million output tokens.

Starting this week, the model is available only to a subset of cyber defenders. Access will expand gradually to other trusted partners through Google's **Fairwind Program**. Google said it is also taking part in the US government's voluntary pre-release model testing process. There is no date yet for developers, businesses and consumers; Google says only that it will come "as soon as possible."

## Sources

1. [Google: Gemini 4 Carbon: our next frontier model, Oct. 28, 2026](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/)
2. [Google AI (X): Announcement post and official key visual, Oct. 28, 2026](https://x.com/GoogleAI/status/2115489593818816591)
3. [Artificial Analysis: Gemini 4 Carbon (High), Oct. 28, 2026](https://artificialanalysis.ai/models/gemini-4-carbon)
4. [Vals AI: Gemini 4 Carbon Benchmarks, Cost and Capabilities, Oct. 28, 2026](https://www.vals.ai/models/google_gemini-4-carbon)
5. [OfficeChai: Gemini 4 Carbon Beats Claude Opus 5.5 On Intelligence While Being 23% Cheaper, Oct. 28, 2026](https://officechai.com/ai/gemini-4-carbon-beats-claude-opus-5-5-on-intelligence-while-being-23-cheaper/)

Report an error: corrections@thejarrus.com