On ConTEB, the preview has the highest average nDCG@10 of the models tested, though not on every task.
Original titleOn ConTEB, the preview has the highest average nDCG@10 of the models tested, though not on every task.
AISummary
It also beats voyage-context-4 on chunk retrieval while using 8x less storage per vector: 1 KB (1024 dims, int8) vs 8 KB (2048, float32).
Source: Perplexity · x.com