AI Trends

GPT-6.2 Astra leads Claude on Agents' Last Exam 1.1…

Yuchen JinUpdated Nov 18 02:03

AI summary

Yuchen Jin says GPT-6.2 Astra scores 5.5 points higher than Claude Fable 5.2 on Agents' Last Exam 1.1, at only 5% of the latter's cost. From this he argues that intelligence-per-dollar should be improved; the tweet includes a link to an image.

Why read this

AI score 56

The tweet gives the score gap and cost ratio between the two models on Agents' Last Exam 1.1, which can be used to observe the cost-effectiveness orientation in agent evaluations.

Topics

Tags

Body

GPT-6.2 Astra beats Claude Fable 5.2 by 5.5 points on Agents' Last Exam 1.1, at just 5% of the cost.

Improve the intelligence-per-dollar! https://t.co/VMyK8zVLiy

Source

Yuchen Jin