List your company

Autonomous Agent Performance on PRDBench

84.67Success RateOneManCompany (Claude Code Sonnet 4.6 + Gemini 3.1 Flash Lite Preview)
8.354828.167447.9867.7926Apr 24, 2026

Evaluation results

MethodLinks
OneManCompany (Claude Code Sonnet 4.6 + Gemini 3.1 Flash Lite Preview)AgentType=Multi-agent2026.0484.67345.59
Claude-4.5AgentType=Minimal2026.0469.19—
GPT-5.2AgentType=Minimal2026.0462.49—
CodeXAgentType=Commercial2026.0462.09—
Claude CodeAgentType=Commercial2026.0456.65—
Qwen3-CoderAgentType=Minimal2026.0443.84—
DeepSeek-V3.2AgentType=Minimal2026.0440.11—
Qwen CodeAgentType=Commercial2026.0439.91—
GLM-4.7AgentType=Minimal2026.0438.39—
Gemini-3-ProAgentType=Minimal2026.0422.76—
Kimi-K2AgentType=Minimal2026.0420.52—
Minimax-M2AgentType=Minimal2026.0417.6—
Gemini CLIAgentType=Commercial2026.0411.29—