List your company

Interleaved Reactive-Proactive Requests on IPIBench

96R2P ScoreHuman Level
-3.8422.084873.92May 26, 2026

Evaluation results

MethodLinks
Human Level2026.0596969896.67
Qwen3.5-PlusModel Type=Open-source, Inference Mode=Offline2026.0532.2522.0130.5728.28
GPT-5.4Model Type=Proprietary, Inference Mode=Offline2026.0527.0415.0629.2823.79
GPT-4oModel Type=Proprietary, Inference Mode=Offline2026.0527.0417.6826.1723.63
Gemini 3 ProModel Type=Proprietary, Inference Mode=Offline2026.0524.7617.6826.6923.04
Qwen3-VL-8BModel Type=Open-source, Inference Mode=Offline2026.0524.4319.7523.0522.41
GLM-4.6VModel Type=Open-source, Inference Mode=Offline2026.0522.156.7739.3722.76
Gemini 2.5 ProModel Type=Proprietary, Inference Mode=Offline2026.0521.1717.5428.2422.32
InternVL3-8BModel Type=Open-source, Inference Mode=Offline2026.057.1709.335.5
LLaVA-OneVision-7BModel Type=Open-source, Inference Mode=Offline2026.053.9103.892.6
VideoLLM-online-8BModel Type=Open-source, Inference Mode=Online2026.0501.11.550.88
Flash-VStream-7BModel Type=Open-source, Inference Mode=Online2026.05000.780.26