Mollick: benchmarks tell us little; Agent Arena may be the best we have

emollick · x · 2026-11-16

Ethan Mollick, replying to Nathan Lambert, agrees that current benchmarking is very limited in what it can tell us. Lambert argued closed models are generally more robust, but judging solely on unmeasurable qualities isn't fair — and suggested Agent Arena may be the best available tool for evaluating agents.

Original post →

More from Models

Models channel →