Benchmarks

HarnessOpt-Bench

Benchmark · From Scale AI · 1 item since Aug 2026

How well models optimize an agent's prompts, tools, control flow, and memory on a fixed budget.

Items

  1. Aug 1

    Scale AI's HarnessOpt-Bench

    A benchmark of how well frontier LLMs optimize an agent's harness (prompts, tools, control flow, memory) under a fixed budget, finding across 111 scored runs that the optimizer model matters more than the coding harness it acts through.