AITechTalks7 months ago
Beyond raw intelligence: How Poetiq cracked the ARC-AGI-2 benchmark
1 min read
AI lab Poetiq scored 54% on the ARC-AGI-2 Semi-Private Test Set, beating the prior state-of-the-art of 45% held by Gemini 3 Deep Think. The system achieved this at $30.57 per problem, less than half the $77.16 cost of Gemini 3 Deep Think.
Level
Hype check
Tap to vote and see what everyone thinks.