中EN Submit a tool
Tip

Anthropic Claude Opus 5 scores 30.2% on ARC-AGI-3 benchmark, far ahead of GPT-5.6 Sol, demonstrating new reasoning behavior

Published: Source: The Decoder: AI News (RSS)

ShareXFacebookTelegramWhatsApp

Anthropic's Opus 5 blows past Fable 5 and GPT-5.6 Sol on the benchmark designed to measure real intelligence

Read the original (opens in a new tab)

News stream data aggregated by AI HOT

Related newsLatest in this category
Tip Moonshot AI's Kimi K3 Model Matches Top US Systems at a Fraction of the Cost, Will Open Weights for Free
· The Verge: AI (RSS)
Tip Doubao Combines Osmo Gameplay, AI Interactive Toys "Evil Cultivation" Upgrade
· X: Berry Xia (@berryxia)
Tip Anthropic Discovers LLM 'Subconscious' J-Space, Can Read Unspoken Thoughts of Models
· X: Vista (@vista8)
Tip China's AI Duo: How Kimi K3 and DeepSeek Are Shaking Silicon Valley
· X: X.PIN (@thexpin)
Tip Getting Started with GitHub Copilot App: Multi-Agent Session Workspace and Canvas Preview
· GitHub Blog