AI Trends

Perplexity launches GPT-6.2 Astra and Sol, WANDR benchmark scores improve

Aravind SrinivasUpdated Nov 18 06:40

AI summary

Perplexity announced that GPT-6.2 Astra and GPT-6.2 Sol are now available in its Search and Computer. On Perplexity's WANDR benchmark, GPT-6.2 Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra; GPT-6.2 Sol scored 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol. Aravind Srinivas reposted that both versions show clear improvements in Wide-and-Deep-Research performance.

Why read this

AI score 53

Perplexity has launched two versions of GPT-6.2 and provided WANDR benchmark scores and per-task costs, allowing comparison of the trade-offs between the two versions on deep research tasks.

Topics

Tags

Quoted post

Perplexity

@perplexity_ai

GPT-6.2 Astra and GPT-6.2 Sol are now available in Perplexity Search and Computer. On our WANDR benchmark, GPT-6.2 Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra. GPT-6.2 Sol hit 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol. https://t.co/TieTVv7w6L

View original

GPT-6.2 Astra and GPT-6.2 Sol are now available in Perplexity Search and Computer. On our WANDR benchmark, GPT-6.2 Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra. GPT-6.2 Sol hit 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol. https://t.co/TieTVv7w6L

View original post

Body

Astra and Sol 6.2 evals on Perplexity. Good improvements on Wide-and-Deep-Research performance

Source

Aravind Srinivas