10 JUN 2026Frontier3 min

Own the harness, swap the model

Public leaderboards compress real differences. The verifier is the hidden variable. The operating conclusion: evaluate on your own work, own the harness and the verification, treat the model as a commodity.

A serious agentic-coding benchmark (DeepSWE: contamination-free, behavior-verified, long-horizon tasks) showed something public leaderboards hide: frontier agents sitting in a 30-point band on SWE-Bench Pro spread across a ~70-point gap. Rankings compress real differences.

The hidden variable is the verifier. Inherited test suites produce 8.5% false positives and 24% false negatives. And scores are harness-relative: the same model inside different harnesses is effectively a different system.

What I do with this, in practice

  • I evaluate models on my own work, with my own scenarios. Leaderboards I read out of curiosity.
  • I own the harness, the tools and the verification. That's where quality lives.
  • I treat the model as a swappable component. When something better ships, I switch in an afternoon.
If you're a decision-maker: ask your team where the evals live. If you're an engineer: if the answer is "in the prompt", you've found the problem.

// happy shipping. or happy debugging, depends on the harness.