Measuring AI Ability to Complete Long Tasks: Opus 4.5 has 50% horizon of 4h49M

Published: 1 week ago (December 20, 2025 at 11:06 PM EST)

1 min read

Source: Hacker News

Article Details

Article URL: https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/
Comments URL: https://news.ycombinator.com/item?id=46342166
Points: 34

Measuring AI Ability to Complete Long Tasks

Article URL: https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/ Comments URL: https://news.ycombinator.com/item?id=46342166 Points: 1...

Gemini 3 Pro scores 69% trust in blinded testing up from 16% for Gemini 2.5: The case for evaluating AI on real-world trust, not academic benchmarks

Just a few short weeks ago, Google debuted its Gemini 3 model, claiming it scored a leadership position in multiple AI benchmarks. But the challenge with vendor...

How to Build an AI Agent Evaluation Framework That Scales

The Scaling Problem So, you've built a great AI agent. You've tested it with a few dozen examples, and it works perfectly. Now, you're ready to deploy it to pr...

When Ai Learns to Admit Its Mistakes Trust Becomes a Real Responsibility

Introduction OpenAI’s latest research direction marks a significant evolution in how advanced AI systems are trained and evaluated, raising fundamental questio...

Article Details

Related posts

Measuring AI Ability to Complete Long Tasks

Gemini 3 Pro scores 69% trust in blinded testing up from 16% for Gemini 2.5: The case for evaluating AI on real-world trust, not academic benchmarks

How to Build an AI Agent Evaluation Framework That Scales

When Ai Learns to Admit Its Mistakes Trust Becomes a Real Responsibility