List your company

Best-action selection on Cross-Domain n=60

73.4Macro F1PIWM (full)
11.83227.81643.859.784Jun 2, 2026

Evaluation results

MethodLinks
PIWM (full)State Conditioning=Oracle2026.0673.4
GPT-5.5Interface=Codex CLI, Protocol=diagnostic, State Conditioning=Oracle2026.0664.8
Gemini 2.5 FlashState Conditioning=Oracle2026.0663.8
Claude Sonnet 4.6State Conditioning=Oracle2026.0656.9
GPT-4oState Conditioning=Oracle2026.0650.3
Random BaselineState Conditioning=Oracle2026.0646.6
State-Outcome ModelState Conditioning=Oracle2026.0625.9
Qwen2.5-VL-7BProtocol=zero-shot, State Conditioning=Oracle2026.0614.2