#11

Amazon Q Developer

🔒 Closed

AWS-integrated AI developer agent with security scanning, multi-file editing, and cloud-native task automation.

💰 Included with AWS subscription · vscode, jetbrains, cli, web, api

64.7Overall Score

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 Opus 4.6	64.7	67.15	71.91	61.35	64.08
Claude Sonnet 4.6	48.7	59.57	44.47	57.19	61.47
Claude Sonnet 4.5	30.7	45	36.78	28.88	42.69
Claude Opus 4.5	29.9	48.16	36.83	21.54	42.71
Claude Opus 4.1	22.5	37.05	34.02	12.58	28.91
Claude Opus 4	17.0	34.65	23.37	7.44	19.67