Exa (formerly Metaphor) vs Perplexity Agent API / Sonar API: what AI actually recommends
The same buying questions, run after run, to ChatGPT, Claude, Gemini, and Perplexity: the record of which of these two they name first. No opinions, no scores we invented: what the models said.
AI currently favors Perplexity Agent API / Sonar API. Ahead in 1 of 1 shared category on consensus rank.
That is the latest close, not a verdict for all time. The model-by-model board below shows where they agree, where they split, and how both brands moved.
At the latest close, Exa (formerly Metaphor) leads 0 and Perplexity Agent API / Sonar API leads 1 across the 1 category they both appear in.
Beyond this pairing, Exa (formerly Metaphor) is ranked in 1 category; Perplexity Agent API / Sonar API is ranked in 1 category. The board below is the shared slice, where the four models place these two side by side.
The record, category by category.
Consensus rank · latest close- #3Perplexity Agent API / Sonar APINew entry at the last closespread 10GPT#2
- #5Exa (formerly Metaphor)New entry at the last closespread 3Gemini#3
On consensus rank, Perplexity Agent API / Sonar API leads here, #3 to Exa (formerly Metaphor)'s #5. 21 to 18 on the 0-100 score. Every model that separates the two ranks Perplexity Agent API / Sonar API ahead. Perplexity Agent API / Sonar API is new to the board at this close.
Where the models split.
Across the 1 category Exa (formerly Metaphor) and Perplexity Agent API / Sonar API share, the models line up cleanly in 0 and split in the 0 that remain.
Model by model, Gemini is Exa (formerly Metaphor)'s strongest backer, placing it ahead in 1 of the 1; ChatGPT leans the other way, favoring Perplexity Agent API / Sonar API in 1.
- ChatGPTfavors Perplexity Agent API / Sonar API 1-0
- Claudesplit 0-0
- Geminifavors Exa (formerly Metaphor) 1-0
- Perplexitysplit 0-0