Xiaomi’s MiMo Code claims it beats Claude Code past 200 steps
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
New coding agent claims to beat Claude Code, highly relevant to AI-assisted development.
Xiaomi's MiMo Code, a terminal-native open-source harness, claims to outperform Claude Code on agentic tasks exceeding 200 steps by targeting the 'endurance gap'—the point where agents lock onto hypotheses and compound errors. A UC Berkeley benchmark, Agents' Last Exam, found even top configurations like Codex with GPT-5.5 score below 50% on easy tasks and under 10% on hard ones, revealing that long-horizon reliability remains unsolved. The field is shifting focus from demo performance to harness-level state management, with Anthropic's nested subagents in Claude Code representing one approach to sustaining coherence across hundreds of steps.