This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
🚨GROK-4 BEATS GPT-5 ON ARC-AGI-2 LEADERBOARD
New ARC-AGI-2 benchmark results show Grok-4 (Thinking) topping the chart, leaving GPT-5 trailing below.
The leaderboard measures reasoning strength versus cost, and Grok-4 sits far ahead in both capability and efficiency compared