Chollet: Benchmark Scores Are Meaningless Without Cost
fchollet · x · 2026-07-07
Keras creator François Chollet believes that reporting a single scalar benchmark score (e.g., "75% on XYZ") is now entirely meaningless. He argues that evaluation results must include an efficiency score, such as "75% at $10 per task," otherwise they fail to reflect the model's true value.
Related event: Chollet: AI Benchmarks Must Include Marginal Costs(2 posts)→
More from Research
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- Terence Tao's SAIR Foundation revamps Mathathon with $1.5M compute per team — _sathvikr · 2026-10-27
- Mathathon 2.0 launches with Terence Tao's SAIR, $1.5M in compute for teams — _sathvikr · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27
- PixGR: Pixel-space generative decoding for fast feed-forward 3D reconstruction — kwangmoo_yi · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27