List your company

Trajectory Completion Judgment on OGRBench Mobile

91AccuracyStainFlow
63.33670.51877.784.882Jun 5, 2026

Evaluation results

MethodLinks
StainFlowVerifier=Gemini-3-Flash2026.069191.3
OS-ThemisVerifier=Gemini-3-Flash2026.0689.990.4
StainFlowVerifier=Qwen3.5-27B2026.0689.490
StainFlowVerifier=Qwen3.5-9B2026.0686.787.3
OS-ThemisVerifier=Qwen3.5-27B2026.0685.686.2
StainFlowVerifier=GPT-52026.0685.687.2
OS-ThemisVerifier=Qwen3-VL-8B2026.0685.184.4
OS-ThemisVerifier=Qwen3.5-9B2026.0685.184.6
OS-ThemisVerifier=GPT-52026.068482.8
StainFlowVerifier=Qwen3-VL-8B2026.068385.6
ZeroGUIVerifier=GPT-52026.0681.483.1
ZeroGUIVerifier=Gemini-3-Flash2026.0680.382.8
ZeroGUIVerifier=Qwen3.5-9B2026.0677.179.2
ZeroGUIVerifier=Qwen3.5-27B2026.0675.578.9
ZeroGUIVerifier=Qwen3-VL-8B2026.0673.479.3
DigiRLVerifier=Gemini-3-Flash2026.0672.971.8
DigiRLVerifier=Qwen3-VL-8B2026.0671.370
DigiRLVerifier=Qwen3.5-27B2026.0667.666.3
DigiRLVerifier=GPT-52026.0664.962.9
DigiRLVerifier=Qwen3.5-9B2026.0664.455.6