List your company

Planning on PlanBench (in-distribution)

97.8Success RateGemini-3-Flash
91.35293.02694.796.374Jun 19, 2026

Evaluation results

MethodLinks
Gemini-3-FlashOrchestrator=prompted2026.0697.82.23.70.06
HALOOrchestrator=ours2026.0695.82.32.60.004
HALOOrchestrator=ours2026.0694.92.12.20.004
GPT-5-miniOrchestrator=prompted2026.06932.84.80.18
Gemini-3-FlashOrchestrator=prompted2026.06932.54.30.06
GPT-5-miniOrchestrator=prompted2026.0691.62.84.80.18