Best LLMs for Science — Perplexity
The best Perplexity model for science is Sonar Pro, scoring 57.8% on GPQA Diamond — graduate-level physics, chemistry and biology. Sonar (47.1%) is next.
- 1
sonar-proVision9.3 intel · $3.00/M · 77 t/s57.8%GPQA - 2sonarVision9.5 intel · $1.00/M · 76 t/s47.1%GPQA
How this is ranked
AI models ranked by GPQA Diamond — graduate-level physics, chemistry and biology questions written to be un-Googleable, so the score reflects reasoning from knowledge rather than retrieval. The best large language models for scientific research and hard-science work.
Frequently asked
What is the best Perplexity model for science?
The best Perplexity model for science is Sonar Pro, scoring 57.8% on GPQA Diamond — graduate-level physics, chemistry and biology. Sonar (47.1%) is next.
What's a good alternative to Sonar Pro?
Sonar (47.1%) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
How many Perplexity models are there?
modelgrep tracks 5 Perplexity models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Sonar Reasoning Pro. 2 of them qualify for this ranking.