Share your thoughts, 1 month free Claude Pro on usSee more

Video Reasoning on Video-Holmes (Accuracy)

60.5Accuracy

VideoChat-M1

Updated 7d ago

Evaluation Results

Method	Links
VideoChat-M1 2025.11		60.5
OmniJigsaw (CMM) 2026.04		52.53
FFR (GLM-4.5V) 2026.04		52.3
OmniJigsaw (SMS) 2026.04		52.26
VideoJigsaw 2026.04		51.99
FFR 2026.04		51.6
Qwen3-Omni-30B 2026.04		50.84
OmniJigsaw (JMI) 2026.04		50.24
OmniJigsaw (CMM) 2026.04		48.29
OmniJigsaw (SMS) 2026.04		47.96
VideoJigsaw 2026.04		47.9
FFR 2026.04		47.8
OmniJigsaw (JMI) 2026.04		47.47
SFT 2026.04		47.1
Qwen3-Omni-30B 2026.04		46.6
Gemini 1.5 Pro 2025.11		45.7
Gemini-1.5-Pro 2026.05		45.7
Mixed RLVR 2026.04		45.62
Video-Expert 2026.04		45.35
Image-Expert 2026.04		44.47
CoPD 2026.04		43.77
MOPD 2026.04		43.33
SFT 2026.04		43.3
Base 2026.04		43.28
Video-Thinker-7B 2026.05		43.1
HumanOmniV2 2026.04		42.9
Qwen3-VL-8B-Thinking + MVP 2026.01		42.6
Text-Expert 2026.04		42.19
Video-R1 2026.04		42.13
GPT-4o 2025.11		42
GPT-4o 2025.11		42
GPT-4o 2026.05		42
Qwen3-VL-8B-Thinking 2026.01		41.8
Claude-3.5 2025.11		41
Video-R1-7B + replay 2025.11		40.9
Omni-R1 2026.04		40.72
Qwen3-VL-8B-Thinking + MVP 2026.01		40.1
InternVL3.5-8B + MVP 2026.01		39.4
InternVL3.5-8B 2026.01		39.3
HumanOmniV2 2026.04		38.87
InternVL3.5-8B + MVP 2026.01		38.8
Omni-R1 2026.04		38.76
Qwen3-VL-8B-Thinking 2026.01		38.5
STORM 2026.05		37.8
InternVL3.5-8B 2026.01		37.7
Jigsaw-7B 2026.01		37.6
Jigsaw-7B 2026.01		36.9
Qwen2.5-VL-7B-Instruct + MVP 2026.01		36.7
EvoVid 2026.05		36.6
VideoChat-R1-7B 2025.11		36.5
Video-R1-7B 2025.11		36.5
Video-R1-7B 2026.05		36.5
EvoVid 2026.05		36.3
Base Model 2026.05		36.2
EvoVid 2026.05		36
Qwen2.5-VL-7B-Instruct + MVP 2026.01		35.9
LongVT-RFT 2026.05		35.5
EvoVid 2026.05		35.2
Qwen2.5-VL-7B-Instruct 2026.01		35
Video-R1-SFT 2026.04		34.6
Qwen2.5-VL-7B-Instruct 2026.01		33.4
VideoChat-R1-7B (Alternative) 2025.11		33
InternVL-3-8B 2025.11		32.3
Qwen2.5-VL-7B-SFT 2026.05		31.4
EvoVid 2026.05		31.1
EvoVid 2026.05		30.7
EvoVid 2026.05		30.4
EvoVid 2026.05		29.9
Base Model 2026.05		29.9
EvoVid 2026.05		29.3
EvoVid 2026.05		29.1
EvoVid 2026.05		28.6
EvoVid 2026.05		28.4
EvoVid 2026.05		28
Qwen2-VL-7B 2025.11		27.8
Qwen2.5-VL-7B 2025.11		27.8
EvoVid 2026.05		27.8
Base Model 2026.05		27.8
Qwen2.5-VL-7B-Instruct(CoT) 2026.05		27.8
EvoVid 2026.05		27.2
EvoVid 2026.05		26.9
Base Model 2026.05		26.8
InternVL-2.5-8B 2025.11		23.6