Great news! Perplexity's Sonar models have co-ranked the #1 spot in the recent LM Search Arena evaluation, with Sonar-Reasoning-Pro-High tying with Google's Gemini-2.5-Pro-Grounding (though it actually beat Gemini-2.5-Pro-Grounding 53% of the time).
Great news! Perplexity's Sonar models have co-ranked the #1 spot in the recent LM Search Arena evaluation, with Sonar-Reasoning-Pro-High tying with Google's Gemini-2.5-Pro-Grounding (though it actually beat Gemini-2.5-Pro-Grounding 53% of the time).