Gemini 4 Carbon Opens to Paying Developers at $2/$10 Until November 30, but Now Sits Fourth on Artificial Analysis Behind Claude Fable 5.2

Updated November 11, 2026: Gemini 4 Carbon is now available to paying developers and Google AI Ultra subscribers, Google has published the end date of its introductory price, and Artificial Analysis no longer ranks it first. The new section directly below covers it; the original report follows unchanged.

November 11: Carbon opens up, and the top spot has moved#

Two weeks after the gated launch described below, Google made Carbon available on November 10 via the Gemini API in Google AI Studio and Gemini for business for all paying developers and enterprises, and began rolling it out to all Google AI Ultra subscribers in the Gemini app, AI Mode in Search and Google Antigravity, Google DeepMind's Koray Kavukcuoglu wrote. The Verge noted that it is not clear when, or if, lower-tier subscribers or free users will get it.

The pricing question left open below now has an answer. Carbon launches at Argon's introductory price of $2 per million input tokens and $10 per million output tokens; after the introductory period expires on November 30, 2026, the price becomes $4 and $20, according to Google's post. Google also extended its free scientist-access programme to Carbon, and the Fairwind Program remains the route to the cyber version.

The independent ranking has moved. On November 11, Artificial Analysis's leaderboard listed Carbon (high) at 60 on its Intelligence Index, fourth behind three settings of Anthropic's Claude Fable 5.2, released on November 9, which score 65, 62 and 62 at max, xhigh and high effort. The leaderboard puts Carbon's cost to run the index at $7.76 per task, against $9.08 for Fable 5.2 (high) and $26.54 for Fable 5.2 (max).

Google's new performance claims are its own. It says Carbon ranks first on CursorBench 4.0, Perplexity's WANDR and Zapier's AutomationBench "at more than 2X lower cost per task compared to the next best external model," and second on a new Multimodal Knowledge Agent benchmark it built with Artificial Analysis. It says its safeguards blocked 99% of attack trajectories from its adaptive red-teaming agent in simulated cyberattack tests. Alongside the release, Google is previewing /swarm in Antigravity, which turns a single prompt into a coordinated team of agents.

Limits of the November 11 update#

• Artificial Analysis gave Carbon 59 on October 28 and lists 60 now; we have not seen an explanation for the change.
• The CursorBench, WANDR, AutomationBench, Multimodal Knowledge Agent and safety figures are Google's reported results; we have not seen independent reproductions.
• Google has not said whether Gemini users below the Ultra tier will get Carbon.

The original report#

Google's newest frontier model is the first to sit on top of Artificial Analysis's new Intelligence Index, and almost nobody can use it yet. Gemini 4 Carbon, announced by Google DeepMind's Koray Kavukcuoglu on October 28, goes first to a subset of cyber defenders through Google's Fairwind program and to the U.S. government's voluntary pre-release testing. Developers, businesses and consumers get it in phases afterwards, on dates Google has not published.

That is the same gated route Google used for Gemini 4 Argon and, before it, for the cyber tier of Gemini 3.8 Flash. The difference this time is that an outside benchmarker has already scored the model, so some of Google's claims can be checked against something other than Google.

What the independent check found#

Artificial Analysis said Carbon scored 59 on its Intelligence Index v5.0, the highest of any model it has tested, and placed first in four of the index's nine evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience and AutomationBench-AA. Google cites the same number-one ranking in its announcement.

The lead is not uniform. On Artificial Analysis's Coding Agent Index, Carbon scored 59, behind Claude Code running Anthropic's Claude Opus 5.5 at 62. On AA-Briefcase, an agentic knowledge-work evaluation, Carbon's 1609 Elo trailed xAI's Grok 4.7, Meta's Muse Wonder and Moonshot's Kimi K3.1 Pro.

Two other findings cut against the launch framing. Artificial Analysis measured a hallucination rate of 11% for Carbon, up from 4% for Argon, even though Google says Carbon makes about half as many unsupported claims as Argon in its own testing. And Carbon used about 123,000 output tokens per index task; at standard pricing, Artificial Analysis put the cost of running its index at $7.76 per task, against $10.04 for Claude Opus 5.5, $6.25 for OpenAI's GPT-6 Astra and $7.68 for Argon.

What only Google has measured#

The cyber numbers, which are the reason for the gated release, are Google's. Google reports 88.2% on SEC-bench Pro, 54.8% on ExploitGym and 71.0% on Collinear's CWE-bench, and says those cyber evaluations were run without guardrails. It says Chrome's security team found Carbon's patches "more than 10X better" than those of an unnamed other lab's large frontier model, and that Carbon delivers more than twice Argon's uplift on secure code in internal evaluations.

Google also reports a gain of 89 Elo points on WebDev Arena, to fourth place, and safety figures from its own and partner tests: 0.0% cheating on Terminal-Bench 4.0, an 80% drop in high-severity misalignment alerts, and a 0.0% indirect prompt-injection success rate on Gray Swan's benchmark, against 0.7% for Argon.

Price and access#

When Carbon reaches the API, Google lists an introductory price of $2 per million input tokens and $10 per million output tokens, rising to $4 and $20, with cached input 95% cheaper. Ars Technica reported that Google declined to say when the introductory price ends; Artificial Analysis also said there is no confirmed end date. Ars noted that the gaps between Carbon and its rivals are a few points on most tests and raised the possibility that the model is a post-training upgrade of Argon. Google has not described how Carbon was built.

Limits#

• Carbon is not yet available to the public, so outside reproduction is limited to Artificial Analysis's access. Its index scores are one independent check, not a consensus.
• The cyber, safety and WebDev Arena figures are Google's own reported results. We did not check the WebDev Arena or LMArena text boards for this report.
• Google has not given dates for developer, enterprise or consumer access, or for the end of introductory pricing.
• Whether Carbon is a new base model or a further-trained Argon is unconfirmed.

Sources#

• Google: Gemini 4 Carbon is now available (November 10, 2026)
• The Verge: Google releases Gemini 4 Carbon with agent 'swarm' feature (November 10, 2026)
• Artificial Analysis: LLM Leaderboard (checked November 11, 2026)
• Google: Introducing Gemini 4 Carbon (October 28, 2026)
• Artificial Analysis: Gemini 4 Carbon is the new #1 in the Artificial Analysis Intelligence Index (October 28, 2026)
• Ars Technica: Google announces Gemini 4 Carbon, its latest frontier AI model that you can't use (October 28, 2026)