gemini-4POST
Gemini 4 Argon tops PPL's WANDR deep-and-wide research agent benchmark
Argon was the best model on PPL's Wide-And-Deep-Research agent benchmark, with a lower task cost than Astra and Fable but higher than Opus 5.5.
忒修斯的船板
@Arcadia_BaoArchived 20 days agoOriginally posted 2026.10.17
忒修斯的船板 @Arcadia_BaoOriginally posted 2026.10.17
Gemini 4 Argon在PPL的深度+广度研究Agent benchmark里拿到最佳模型，任务成本低于Astra和Fable、高于Opus5.5，结果表现则最好： （Wide-And-Deep-Research WANDR）
This post quotes another post: “Perplexity adds Gemini 4 Argon for Pro and Max subscribers”
x.com/arcadia_bao/status/2111125196124143877Archived 2026.10.17 10:04