antirez: stellar cybersec benchmarks aside, wait for real user testing before trusting the best scores

antirez · x · 2026-09-10

antirez continued his take on the new DeepSeek model: benchmarks in areas like cybersecurity look terrific — a huge use case — but other benchmarks align more with past performances. He advises waiting for real user testing before trusting the best benchmark scores as a general proxy for capability.

Related event: antirez Questions DeepSeek's New Model: Impressive Scores, Wait for Real Users(3 posts)→

Original post →

More from Models

Models channel →