MMLU-Pro holds steady at 85.0, AIME 2025 slightly improves to 89.3, while GPQA-Diamond dips from 80.7 to 79.9. Coding and agent benchmarks tell a similar story, with Codeforces ratings rising from ...
The new Search API is the latest in a series of rollouts as Perplexity angles to position itself as a leader in the nascent ...
Perplexity launches its “Perplexity Search API,” offering fine-grained indexing, rich structured responses, and flexible ...
Discover Perplexity's new Search API, giving developers real-time access to a vast web index for advanced AI apps.
Perplexity AI launches comprehensive search API giving developers access to hundreds of billions of web pages, challenging ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results