News Google
Gemini 4 Carbon: Google’s new model arrives 15 days after Argon
Official cover from Google. Benchmarks from Google’s published table and methodology.
Google announced Gemini 4 Carbon on October 28, fifteen days after introducing Argon. The company describes it as its strongest model for cybersecurity and long-horizon tasks. The announcement is official; access is beginning with a limited group of cyber defenders.
If you had just settled on Argon, this is a quick follow-up: Google introduced it on October 13. Sundar Pichai presented Carbon on X; Koray Kavukcuoglu wrote the official blog post. Google’s announcement · Sundar Pichai’s post.
What the benchmarks show
Google says Carbon scored 59 on Artificial Analysis Intelligence Index v5.0, the highest figure in the comparison table it published: Argon scored 50, GPT-6 Astra 57, Claude Opus 5.5 58, and Claude Fable 5.1 49. These figures come from Google’s published comparison. Its methodology identifies the index version with tools and explains how each result was obtained.
There is no universal winner in the table. On FrontierSWE 2, GPT-6 Astra scores 65.5%, ahead of Opus 5.5 (62.3%) and Carbon (61.2%). On OSWorld-2.1’s offline subset, Opus 5.5 leads at 87.2%; Carbon scores 81.5%. Google published these results for different tests, with distinct metrics and conditions that should not be collapsed into one ranking.
For cybersecurity evaluations, Google reports 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching. The company says the external evaluations were run without guardrails. The charts identify some conditions—such as per-task time caps for ExploitGym and agent/tool labels for CWE-bench—and the methodology expands on those conditions. Carbon and Argon use the highest thinking settings unless otherwise noted; Google cites the highest available or best published reasoning results for competitors. Google’s table credits the Gemini 4 Carbon evaluations methodology.
In ExploitGym, Carbon’s 54.8% uses a ten-hour cap per task; at six hours, Google reports 53.5%. Opus is listed at six hours and Astra without a cap. These are different budgets, not a comparison with identical runtime.
Google also cites internal safety and coding evaluations. These are company-reported results, not independent audits. A 0.0% attack-success figure in the Gray Swan chart applies to the evaluated attacks at the displayed k=15 level; it does not mean the model is immune to attacks. The post also says successful cheating on Terminal-Bench 4.0 was 0.0%, while cheating attempts were 0.4%.
Where Carbon leads, and where it trails
Google’s published comparison · Oct 28, 2026
AA Index v5.0 · index · higher is better
Artificial Analysis’ composite index as reported in Google’s table. This is not a HeyMark-computed average.
| Benchmark | Gemini 4 Carbon | Gemini 4 Argon | GPT-6 Astra | Claude Opus 5.5 | Claude Fable 5.1 |
|---|---|---|---|---|---|
| AA Index v5.0 | 59 | 50 | 57 | 58 | 49 |
| Vals Index v2.2 | 70.4% | 69.2% | 65% | 70.2% | — |
| SWE-sweep | 9.6% | 4.3% | 9.5% | 3.6% | 2.9% |
| FrontierSWE 2 | 61.2% | 55% | 65.5% | 62.3% | 56.3% |
| Terminal-Bench 4.0 (AA) | 65.2% | 57.1% | 59.1% | 59.6% | 52% |
| Agents’ Last Exam v1.1 — Score | 77.4% | 69% | 73.1% | 71.6% | — |
| OSWorld-2.1 — Offline subset | 81.5% | 74.7% | 80.9% | 87.2% | 76.8% |
| AutomationBench — Zapier | 53.9% | 51.3% | 41.4% | 42.5% | 31.4% |
| Vending-Bench 2 — Bank balance (USD) | US$ 16,484 | US$ 13,718 | US$ 15,515 | US$ 9,235 | US$ 5,422 |
| Chartography | 72.5% | 71.6% | 71% | 66.3% | 46.2% |
| Blueprint-Bench 2 — Similarity score | 58.6% | 54.4% | 49.7% | 51.2% | 41.9% |
| GraphWalks — 256k to 1M, BFS (F1) | 96.2% | 84.2% | 71.8% | 66.8% | 65% |
| RiemannBench | 80% | 76% | 72% | 69.6% | 65.6% |
| Terminal-Bench-Science 0.1 (AA) | 64.8% | 52.9% | 63.3% | 59% | 43.3% |
| CWE-bench — Pass@1 / Pass@4 tie-break | 71% | 68% | 68% | 67% | 58% |
| ExploitGym — Causal pass rate | 54.8% | 42% | 42.4% | 34.5% | — |
| SEC-bench Pro — Pass@1 | 88.2% | 83.4% | 85.4% | — | — |
What changes for long-running tasks
Google says its internal teams have used Carbon for days to investigate bugs and complete multi-step engineering work. That is an internal company observation, not a HeyMark test or a duration guarantee for any task. If you use agents, the useful question is whether they finish the job while respecting its constraints; hours of runtime alone do not establish that. Google’s announcement and examples.
Pricing and access
Google announced introductory pricing of $2 per million input tokens and $10 per million output tokens. Cached input tokens are 95% off the input-token price. After the introductory period, pricing will be $4 and $20 per million, respectively; Google has not said when the initial pricing ends.
Access starts this week with a limited group of cyber defenders. Google plans to expand gradually to trusted partners through its Fairwind Program. Developer, business, and consumer access is expected later, with no specific public date.
| Rate | Input | Output |
|---|---|---|
| Introductory | $2 | $10 |
| After the introductory period | $4 | $20 |
Estimate your token volume
Compare both rates for the same input and output volume. This calculation uses uncached input.
Enter whole amounts from 0 to 1 billion in both fields.
- Introductory
- USD 4.50
- After the introductory period
- USD 9.00
Calculated example using announced rates, not a measured bill. Excludes caching, tools, tax and other services. Amounts can span multiple requests and do not indicate context-window size.
Pricing does not confirm public access. Google gives no end date for the introductory period. The announced 95% discount applies to cached input, not output. Source ↗
What is known—and what is not
Carbon follows Argon by two weeks, according to Google. The sequence signals a brisk release cadence, but does not mean Carbon replaces Argon or leads every task. Google’s table shows different strengths: Astra leads the cited FrontierSWE 2 result, while Opus 5.5 leads on OSWorld-2.1 offline.
For now, the available information consists of results reported by Google, announced pricing, and a phased rollout. Google has not given a general availability date. It does publish methodology: OSWorld uses 82 offline tasks and, for Gemini, the highest score across three runs, with one attempt per run; Agents’ Last Exam uses 122 tasks, a five-hour window and the October 17 task version without the October 26 update. Those conditions matter beyond a headline score.
Sundar Pichai’s original announcement
Sundar Pichai introduces Gemini 4 Carbon · October 28, 2026. The post confirms initial access for cyber defenders and a later expansion to Fairwind partners.
Source
Plan your next post in HeyMark.
Keep the idea, review the draft with your team, and see how it performed in the accounts you connected.