ARC Prize’s verified testing puts Gemini 4 Hydrogen at 92.5% on ARC-AGI-2 at $1.26 a task and 98.5% on ARC-AGI-1, using about 52% fewer reasoning tokens than Gemini 3.8 Flash. Google says the fast model, built for everyday agentic work, is now in the Gemin...
VQV Signal
Google’s Gemini 4 Hydrogen scores a verified 92.5% on ARC-AGI-2 and rolls out in the Gemini app and Search
ARC Prize’s verified testing puts Gemini 4 Hydrogen at 92.5% on ARC-AGI-2 at $1.26 a task and 98.5% on ARC-AGI-1, using about 52% fewer reasoning tokens than Gemini 3.8 Flash. Google says the fast model, built for everyday agentic work, is now in the Gemin...
ARC Prize’s verified testing puts Gemini 4 Hydrogen at 92.5% on ARC-AGI-2 at $1.26 a task and 98.5% on ARC-AGI-1, using about 52% fewer reasoning tokens than Gemini 3.8 Flash. Google says the fast model, built for everyday agentic work, is now in the Gemini app and Search, putting it directly in front of everyday...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
VQV surfaced this signal because it is recent, relevant to Consumer AI, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.