Video
Napredni modeli kompanija OpenAI i Anthropic u posljednje vrijeeme vode žestoku borbu, pri čemu se svaka hvali pobjedama u različitim kategorijama. Sada se Google umješao sa svojim najnovijim modelom Gemini 4 Carbon, hvaleći se vrhunskim rezultatima na testovima u ključnim oblastima kao što su sajber-bezbednost i programiranje, piše B92.
“Zasnovan na modelu Gemini 4 Argon, koji je predstavljen prije dvije nedjelje, Carbon ilustruje brzinu kojom pomjeramo granice mogućeg”, napisala je kompanija u objavi.
Introducing Gemini 4 Carbon, our latest frontier model. Carbon delivers improved performance across domains — ranking #1 on v5.0 of the @ArtificialAnlys Intelligence Index and sets a new state-of-the-art in cybersecurity and long-horizon capabilities. It’s rolling out starting this week to cyber defenders through our Fairwind Program, with expanded access coming soon 🧵
— Google (@Google) October 28, 2026
Testovi kompanije pokazuju da Gemini 4 Carbon ostvaruje najviši rezultat od 59 poena na AA Index v5.0 (opšti test za vještačku inteligenciju), čime se našao tik ispred modela Claude Opus 5.5 i GPT-6 Astra. Google takođe tvrdi da je ostvario skoro potpunu dominaciju u svim kategorijama, uključujući agentsko programiranje, korišćenje računara, intelektualni rad, nauku i matematiku, kao i u drugim oblastima. Google je posebno istakao dominaciju Carbona u oblasti sajber-bezbjednosti, gdje je nadmašio druge modele sa prilično velikom razlikom.
Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index Gemini 4 Carbon scores 59 on Intelligence Index v5, driven by leading performance in complex reasoning, knowledge, and scientific tasks. It also has large gains in coding and knowledge work, particularly when compared to other Gemini models, but it is not leading in all these areas. As with launch of Gemini 4 Argon, Gemini 4 Carbon is being rolled out to selected users and is not yet publicly available. Google is offering a 50% launch discount, with no confirmed end date. All our charts and figures use standard pricing for both Gemini 4 Carbon and Argon. Key results for Gemini 4 Carbon with high reasoning: ➤ Gemini 4 Carbon leads the Intelligence Index v5, with the #1 score in 4 of the 9 Index evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, AutomationBench-AA. Carbon makes substantial gains elsewhere but is not leading in coding and knowledge work ➤ Behind only Claude Opus 5.5 on coding agents: With Antigravity CLI, Gemini 4 Carbon (high) scores 59 only 3 points behind Claude Code with Claude Opus 5.5 (max, 62) on the Artificial Analysis Coding Agent Index. Carbon ranks second on both Terminal-Bench 4.0 (64%) and FrontierCode v1.1 (51%), behind Claude Opus 5.5 (max) at 56%. Google has historically underperformed in this area and so this improvement stands out ➤ Improved agentic knowledge work, but not yet leading: On AA-Briefcase, Gemini 4 Carbon (high) scores 1609 Elo, a 126-point improvement over Gemini 4 Argon (high, 1483), but still behind models including Grok 4.7 (xhigh, 1638), Muse Wonder (max, 1659) and Kimi K3.1 Pro (1678). The largest gain comes from Presentation, up 293 Elo to 1598, alongside a 120-point improvement in Analytical Quality to 1671 ➤ Lower Cost per Task than Claude Opus 5.5 for comparable overall intelligence: Gemini 4 Carbon costs $7.76 per Intelligence Index task, ~23% less than Claude Opus 5.5 (max, $10.04) but ~1.2x GPT-6 Astra (max, $6.25). It uses 123k output tokens per task, 29% fewer than Claude Opus 5.5 (max, 173k). At the same $4/$20 standard pricing, its Cost per Task is in line with Gemini 4 Argon ($7.68), while scoring 9 points higher on the Intelligence Index ➤ Leading AA-Omniscience v1.1 score, with low hallucination: Gemini 4 Carbon scores 54 on our recently updated AA-Omniscience v1.1, 6 points ahead of Claude Opus 5.5 (max, 48) and 8 points ahead of Gemini 4 Argon (46). Accuracy (% correct) rises 10 points over Argon to 58%, while its hallucination rate rises from 4% to 11%. This is still the second lowest of any model, behind only Argon, compared with 50% for both Claude Opus 5.5 (max) and GPT-6 Astra (max) Key model details: ➤ Context Window: 1M tokens ➤ Multimodality: Text, image, video, and speech input, with text output ➤ Pricing: $4/$20 per 1M input/output tokens, the same as Gemini 4 Argon’s standard pricing, with a 50% discount. Cached input tokens receive a 95% discount ($0.20 per 1M) Congratulations to the @GoogleDeepMind team!
— Artificial Analysis (@ArtificialAnlys) October 28, 2026
Kao što je bio slučaj i sa prethodnim naprednim modelima, Carbon će u početku biti dostupan samo odabranim kompanijama za sajber-odbranu, kako bi se omogućilo testiranje modela prije zvaničnog objavljivanja.
Preporučeno
Google će s vremenom omogostupiti pristup i drugim partnerima od poverenja kroz svoj program Fairwind, prije nego što ga pusti u široku upotrebu. To je upravo ono što je Google uradio i sa modelom Gemini 4 Argon, koji je sada dostupan u aplikaciji Gemini i u režimu pretrage pomoću vještačke inteligencije (AI search mode).
