A 17-point difference between Anthropic’s and Vals AI’s Terminal-Bench results cannot be read as a verdict on either model. It shows that an agent benchmark measures a configured run—not model weights alone.
01 · Tech News
Follow the AI industry.
115 reports following 53 companies and partnerships from model release to physical deployment.
All Tech News
Browse every report, including the current lead.
Tag: Anthropic / Terminal-Bench
1 article · By event date