AI Trends

GPT-6.2 Astra Sets a New Record on Agents’ Last Exam

Vaibhav SrivastavUpdated Nov 18 02:59

AI summary

GPT-6.2 Astra set a new record on Agents’ Last Exam, which tests multi-step professional work, scoring 5.2 points higher than GPT-6 Astra at less than one-third of its cost; it also scored 5.5 points higher than Claude Fable 5.2 at only 5% of its cost. The results come from a tweet introducing GPT-6.2 Astra and Sol, both of which are now available on ChatGPT Work, Codex, and the OpenAI API.

Why read this

SelectedAI score 80

The original text provides Astra's score gap and cost comparison against GPT-6 and Claude Fable 5.2 on Agents’ Last Exam, which can be used to assess changes in cost-effectiveness.

Topics

Tags

Quoted post

Vaibhav (VB) Srivastav

@reach_vb

Introducing GPT-6.2 Astra and Sol ✨ Astra for your hardest projects. Sol for strong results at a fraction of the cost. 💻 Cleaner code and better frontends 📊 Slides and spreadsheets that follow your template 🔬 Stronger reasoning on scientific tasks > Agents’ Last Exam: 6.2 Astra at xhigh scores 5.2 points above GPT-6 Astra at max, at less than half the cost per task > FrontierCode 2.0: Sol nearly matches Astra on merge-ready changes to real codebases at about one-fifth the cost > GDPval v2: Astra outperforms GPT-6 Astra on multistep projects in consulting, finance, and design, using 22% fewer output tokens Rolling out today in ChatGPT Work and Codex, and available in the OpenAI API. API pricing per 1M tokens: > Astra: $8 input / $0.40 cached input / $40 output > Sol: $2 input / $0.10 cached input / $10 output Excited to see what you all cook with these 🔥

View original

Introducing GPT-6.2 Astra and Sol ✨ Astra for your hardest projects. Sol for strong results at a fraction of the cost. 💻 Cleaner code and better frontends 📊 Slides and spreadsheets that follow your template 🔬 Stronger reasoning on scientific tasks > Agents’ Last Exam: 6.2 Astra at xhigh scores 5.2 points above GPT-6 Astra at max, at less than half the cost per task > FrontierCode 2.0: Sol nearly matches Astra on merge-ready changes to real codebases at about one-fifth the cost > GDPval v2: Astra outperforms GPT-6 Astra on multistep projects in consulting, finance, and design, using 22% fewer output tokens Rolling out today in ChatGPT Work and Codex, and available in the OpenAI API. API pricing per 1M tokens: > Astra: $8 input / $0.40 cached input / $40 output > Sol: $2 input / $0.10 cached input / $10 output Excited to see what you all cook with these 🔥

View original post

Body

New high on Agents’ Last Exam, which tests multistep professional work.

GPT‑6.2 Astra scores 5.2 points above GPT‑6 Astra at less than a third of the cost, and 5.5 points above Claude Fable 5.2 at just 5% of the cost.

Source

Vaibhav Srivastav