Cursor

AI-first code editor with inline completions, multi-file editing, and contextual codebase understanding.

89.5+0.7% (24h)

Non-Gameable Scoring

Scores are derived from established benchmarks, adjusted for harness-specific performance across four dimensions: Coding, Reasoning, Tool Use, and Autonomy.

Each dimension starts from public benchmark data and applies harness-specific modifiers based on tool integration, context handling, and orchestration quality. The overall score is a weighted composite that penalizes narrow optimization.

Model	Overall	Coding	Reasoning	Tool Use	Autonomy
Claude Sonnet 4.6	91.8	96	88	90	85
GPT-5.4	89.2	93	87	88	83
Gemini 2.5 Pro	87.1	90	85	86	81