Google unveils Gemini 4 Carbon, its next frontier AI model
Google announced Gemini 4 Carbon, saying it ranks first on the Artificial Analysis Intelligence Index v5.0 with a score of 59. It comes two weeks after Gemini 4 Argon and will first go to a group of cyber defenders.
- Google says Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5.0 with a score of 59
- It will first be available to a subset of cyber defenders this week
- Introductory pricing is $2 per million input tokens and $10 per million output tokens
Google announced Gemini 4 Carbon on Wednesday, describing it as its next frontier model. It was unveiled two weeks after the launch of Gemini 4 Argon.
Google says Carbon ranks first on the Artificial Analysis Intelligence Index v5.0, with a score of 59. The company also said it jumped 89 Elo points to 1768, placing it fourth on WebDev Arena. Google said it improved the model in full-stack web development, scientific tasks and multimodal understanding, based on user feedback.
On cybersecurity tests, Google reported that Carbon scored 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation and 71.0% on CWE-bench for patching. Google's Chrome team reported that Carbon performed more than 10 times better than another lab's large frontier model at generating high-quality patches, and Wiz observed Carbon leading on benchmarks for web penetration testing.
Google said that on internal benchmarks Carbon achieves more than double the success rate of Argon in generating secure code. In its words, "On internal benchmarks, Carbon drives a strong uplift in generating secure code, and in live coding environments with our own teams it shows reduced misalignment and fabrication rates." High-severity misalignment alerts in internal live coding environments dropped by almost 80%, according to Google.
The company also reported that successful cheating on Terminal-Bench 4.0 fell to 0.0%, with attempts at 0.4%. In internal testing, Carbon cut unsupported claims by about half compared with Argon and reduced task overreach by 26% and under-service by 29% in multi-step workflows. Google said the model retrieves relevant sources and surfaces discrepancies to users when facing ambiguity.
On release, Google said it is taking part in the U.S. government's voluntary process for pre-release model testing. Carbon will first be made available to a subset of cyber defenders this week, then to additional trusted partners through the Fairwind Program. Google plans to release it to developers, businesses and consumers after gathering feedback and refining guardrails.
Introductory pricing matches Argon at $2 per million input tokens and $10 per million output tokens, with cached input tokens priced 95% below the input rate. Anadolu Agency reported that standard pricing will later rise to $4 per million input tokens and $20 per million output tokens. All performance figures are Google's own claims.
Why it matters
Many people in Pakistan use Gemini-based tools for work, study and freelancing, so a new frontier model affects them directly. Google says broader release to developers, businesses and consumers will follow the initial cyber defender access.
