Gemini 4 Carbon
Google · Released Oct 2026
Conditional. Gemini 4 Carbon is Google's strongest model by its own account, announced October 28, 2026 with what Google calls state-of-the-art cyber results, but access is limited to a subset of cyber defenders and trusted partners through the Fairwind Program. Every figure is Google's own and we have not tested it. Right for security teams that can qualify; everyone else has to wait for the broader release, which Google has not dated.
Is it right for you?
Good for
- Vulnerability discovery, exploitation and patching research by defenders who qualify for access; Google reports SEC-bench Pro 88.2%, ExploitGym 54.8% and CWE-bench 71.0% (Google's claims, untested by us)
- Secure code generation; Google says Carbon delivers more than 2x uplift in success rate over Argon (Google's claim)
- Security agents exposed to untrusted content; Google reports 0.0% attack success on Gray Swan's indirect prompt injection benchmark, down from Argon's 0.7% (Google's claim)
Not good for
- Anyone outside the defender and Fairwind partner groups; the post says a subset of cyber defenders first, then additional trusted partners, and developers, businesses and consumers only "soon"
- Budgeting beyond the introductory price; the post gives $4 input and $20 output per 1M tokens after the introductory period and states no end date
- Decisions that need independent benchmark confirmation; every figure comes from Google's announcement, including the Artificial Analysis figure of 59, which we did not check against Artificial Analysis
- Planning around context size or an API id; the post gives neither, and the Gemini API pricing page and changelog we read list no Carbon entry
How it performs by task
Vulnerability discovery
SEC-bench Pro 88.2%, called state-of-the-art by Google; vendor claim, untested by us
Exploit generation
ExploitGym 54.8%, called state-of-the-art by Google; vendor claim, untested by us. Gated access limits who can use it
Patching
CWE-bench 71.0% on Collinear's benchmark per Google; vendor claim, untested by us
Prompt-injection robustness
0.0% attack success on Gray Swan's indirect prompt injection benchmark per Google, against Argon's 0.7%; vendor claim, untested by us
Pricing
Input
$2 / 1M tokens (intro)
Output
$10 / 1M tokens (intro)
Context
Intro rate, then $4/$20; gated, no API id
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| SEC-bench Pro (Google-reported) | 88.2% | Source |
| ExploitGym (Google-reported) | 54.8% | Source |
| CWE-bench (Google-reported) | 71.0% | Source |
| WebDev Arena (Google-reported) | #4 (1768) | Source |
| Artificial Analysis Intelligence Index v5.0 (as stated by Google) | 59 (#1) | Source |
| Gray Swan indirect prompt injection attack success rate (Google-reported, lower is better) | 0.0% | Source |
No verdict changes yet
The clock starts day one. Changes land here as our verdict evolves.
Sources
Verification log
- Pricing· No changes
Automated agent