Google's Gemini 4 Argon is closer to the AI frontier than any Google model in months
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Google Deepmind's new frontier model, Gemini 4 Argon, achieved a 97.5 percent score on the ARC-AGI-3 benchmark at a cost of $4,800 using the Provider Adapter Harness, making Google the second lab after OpenAI to surpass 95 percent on the test. However, Argon's score drops to 49.8 percent in the Standard Harness, and the model trails competitors in mathematics and software engineering.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu