List your company

Trajectory completion judgment on OGRBench (Overall)

88.2AccuracyStainFlow
61.1668.1875.282.22Jun 5, 2026

Evaluation results

MethodLinks
StainFlowVerifier=Gemini-3-Flash2026.0688.287.58988.2
StainFlowVerifier=Qwen3.5-27B2026.0687.486.488.687.5
OS-ThemisVerifier=Gemini-3-Flash2026.0686.688.484.186.2
OS-ThemisVerifier=Qwen3.5-27B2026.0686.4898385.6
StainFlowVerifier=Qwen3.5-9B2026.0684.783.885.784.8
ZeroGUIVerifier=Qwen3.5-27B2026.0684.582.287.984.9
StainFlowVerifier=GPT-52026.0683.580.68884.2
ZeroGUIVerifier=GPT-52026.0681.980.683.782.1
ZeroGUIVerifier=Gemini-3-Flash2026.0681.580.183.681.8
StainFlowVerifier=Qwen3-VL-8B2026.0681.175.591.982.9
OS-ThemisVerifier=Qwen3.5-9B2026.0680.786.372.778.9
ZeroGUIVerifier=Qwen3.5-9B2026.0680.176.985.781.1
OS-ThemisVerifier=GPT-52026.0680.189.967.477.1
OS-ThemisVerifier=Qwen3-VL-8B2026.0679.184.970.477
ZeroGUIVerifier=Qwen3-VL-8B2026.067769.894.780.4
DigiRLVerifier=Gemini-3-Flash2026.0669.480.750.462
DigiRLVerifier=GPT-52026.0667.278.147.358.9
DigiRLVerifier=Qwen3.5-27B2026.0667.180.544.757.5
DigiRLVerifier=Qwen3-VL-8B2026.06667646.157.4
DigiRLVerifier=Qwen3.5-9B2026.0662.281.131.345.2