Benchmark evaluation is effectively impossible for long-horizon real-world agent tasks, for many reasons including cost.

Added to korrents 24 Oct 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. NBNoam Brown26 Jun 2026benchmarks
• A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. DRDax Raad3 Sept 2026benchmarks
• A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost. TPThuan Pham1 Apr 2026benchmarks
• A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. THThePrimeagen22 Mar 2025benchmarks
• AI is positively reinforced for success on benchmarks, including impossible ones, and then negatively reinforced for getting caught cheating. SAScott Alexander1 Sept 2026benchmarks

See this claim on the map