List your company

Proactive Task Management on IPIBench

98Cancel ScoreHuman Level
-2.474423.610349.69575.7797May 26, 2026

Evaluation results

MethodLinks
Human Level2026.0598929896
GPT-5.4Model Type=Proprietary, Inference Mode=Offline2026.0538.4324.57.5723.5
Gemini 2.5 ProModel Type=Proprietary, Inference Mode=Offline2026.0524.5420.8116.7820.71
Gemini 3 ProModel Type=Proprietary, Inference Mode=Offline2026.0519.4421.8419.3920.22
GLM-4.6VModel Type=Open-source, Inference Mode=Offline2026.0515.2824.169.6916.38
Qwen3.5-PlusModel Type=Open-source, Inference Mode=Offline2026.0512.9631.5410.8718.46
GPT-4oModel Type=Proprietary, Inference Mode=Offline2026.0511.5731.8814.1819.21
VideoLLM-online-8BModel Type=Open-source, Inference Mode=Online2026.057.871.686.625.39
InternVL3-8BModel Type=Open-source, Inference Mode=Offline2026.056.946.043.555.51
Flash-VStream-7BModel Type=Open-source, Inference Mode=Online2026.052.31000.77
LLaVA-OneVision-7BModel Type=Open-source, Inference Mode=Offline2026.051.391.010.470.96
Qwen3-VL-8BModel Type=Open-source, Inference Mode=Offline2026.051.3917.459.229.35