List your company

Long Video Understanding and Reasoning on VideoSIAH Eval

42AccuracyLongVT-7B-RFT
5.18414.74224.333.858Nov 25, 2025

Evaluation results

MethodLinks
LongVT-7B-RFTReasoning Prompt=true, Tool Calling=true, Frame Sampling Regime=Dense2025.114247.7
LongVT-7B-RLReasoning Prompt=true, Tool Calling=true, Frame Sampling Regime=Dense2025.1135.946.6
LongVT-7B-SFTReasoning Prompt=true, Tool Calling=true, Frame Sampling Regime=Dense2025.1134.844.1
Qwen2.5-VL-7BReasoning Prompt=false, Tool Calling=false, Frame Sampling Regime=Dense2025.1133.846
Video-R1-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Dense2025.1133.142.7
LongVT-7B-RLReasoning Prompt=true, Tool Calling=true, Frame Sampling Regime=Sparse2025.113143.7
Qwen2.5-VL-7BReasoning Prompt=false, Tool Calling=false, Frame Sampling Regime=Sparse2025.1128.137.2
Video-R1-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Sparse2025.1127.942.6
VideoRFT-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Dense2025.1126.937
LongVT-7B-SFTReasoning Prompt=true, Tool Calling=true, Frame Sampling Regime=Sparse2025.1126.836.2
VideoRFT-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Sparse2025.1126.542.3
GPT-4oReasoning Prompt=false, Tool Calling=false2025.1117.451.5
Video-Thinker-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Sparse2025.1110.442.6
Video-Thinker-7BReasoning Prompt=true, Tool Calling=false, Frame Sampling Regime=Dense2025.116.642.9