TokenPost·
Artificial Analysis Finds 770-Point Elo Gap Across 40 AI Models
770-point
Elo gap
GPT-4o (Nov. ’24) scored 1,467 Elo on sycophancy, while Grok 4.7 (Xhigh) scored 697. The benchmark tests 30 personality traits with 900 questions.
More news
- TokenPostAmazon Agrees to Withdraw Data Center Plan and Dedicate Roughly 25 Acres
- TokenPostSpread on Fox’s Planned $22 Billion Roku Deal Narrows to $2.06
- TokenPostZebec Network Buys Back 40.5 Million ZBCN Tokens in Q3
- TokenPostBaidu’s AI Business Grows 25% as Online Marketing Revenue Falls 19%
- TokenPostComet Cloud Targets Small Businesses With Dedicated GPU Clusters
- Bitcoin.com NewsInterior Photos Can Reveal a Home Address, a Police AI Test Shows