The Decoder 🧠 Models 👁 0 ⏱ 1 min read

Google's Gemini 4 Argon is closer to the AI frontier than any Google model in months

Google Deepmind's Gemini 4 Argon scored 97.5 percent on the ARC-AGI-3 benchmark, making Google the second lab after OpenAI to cross the 95 percent mark. But the results swing wildly depending on the test setup: in the standard harness, the score drops to just 49.8 percent. Argon also trails rivals…

Annons
Annons
Google Deepmind's Gemini 4 Argon scored 97.5 percent on the ARC-AGI-3 benchmark, making Google the second lab after OpenAI to cross the 95 percent mark. But the results swing wildly depending on the test setup: in the standard harness, the score drops to just 49.8 percent. Argon also trails rivals in math and software engineering. The article Google's Gemini 4 Argon is closer to the AI frontier than any Google model in months appeared first on The Decoder.

Source: The Decoder — Published — Category: Models

🔗 Read full article on The Decoder →
🏷️ Topics: GeminiOpenAIGoogleDeepMindAGI

More from The Decoder today

ChatGPT becomes a full Chrome browser assistant that reads and acts on your open tabs 11h ago China plans to tighten export controls on open-weight models and 23 key AI technologies 11h ago Is AI interpretability close to a breakthrough? A new essay has researchers divided 15h ago

More in Models

OpenAI10h ago

How Itaú is building generative AI for its entire customer base
The Decoder11h ago

ChatGPT becomes a full Chrome browser assistant that reads and acts on your open tabs
The Decoder11h ago

China plans to tighten export controls on open-weight models and 23 key AI technologies
The Decoder15h ago

Is AI interpretability close to a breakthrough? A new essay has researchers divided
The Decoder16h ago

OpenAI's new Rosalind Academic Plan gives research labs up to 30 free seats for a year
The Decoder16h ago

Anthropic gives METR inside access to audit its AI models and safety practices
Annons
Annons