antirez: LLM benchmarking is broken—we need jointly lab-funded trusted third parties

antirez · x · 2026-11-19

antirez argues that LLM benchmarking is broken because there are no trusted third parties running evaluations. His proposed fix: benchmarks run by organizations jointly funded by AI labs—not VCs—that primarily run benchmarks where models compete against each other on tasks.

Original post →

More from Models

Models channel →