Our new X account is live! Follow @wizwand_team for updates

Video Question Answering on VideoMME

85.1Accuracy

Gemini 2.5 Pro

Updated 3d ago

Evaluation Results

Method
Gemini 2.5 Pro 2026.01	85.1	-	-	-	-	-	-
Gemini 1.5 Pro 2026.01	78.6	-	-	-	-	-	-
Gemini-1.5-Flash 2026.01	76.1	-	-	-	-	-	-
Gemini 1.5 Pro 2024.10	75	-	-	-	-	-	-
Gemini-1.5-Pro 2025.02	75	-	-	-	-	-	-
Gemini-1.5-Pro 2026.02	75	-	-	-	-	-	-
Qwen3-VL-8B 2026.01	72.5	-	-	-	-	-	2.2
GPT 4o 2024.10	71.9	-	-	-	-	-	-
GPT-4o 2025.02	71.9	-	-	-	-	-	-
GPT4-o 2026.02	71.9	-	-	-	-	-	-
VideoAuto-R1 2026.01	71.7	-	-	-	-	11	52
Qwen2-VL-7B-Instruct 2026.01	71.4	-	-	-	-	-	-
Gemini-1.5-Flash 2025.02	70.3	-	-	-	-	-	-
LLaVA-Video-7B+TIR-Flow 2026.01	68.9	-	-	-	-	-	-
Qwen2.5-VL-7B+TIR-Flow 2026.01	68.3	-	-	-	-	-	-
VideoAuto-R1 2026.01	67.3	-	-	-	-	40	44
LOVE-R1 2026.01	66.2	-	-	-	-	-	-
VideoLLaMA3-7B 2026.01	66.2	-	-	-	-	-	-
Qwen2.5-VL-7B 2026.01	66	-	-	-	-	-	3
LongVU 2025.03	65.4	-	-	-	-	-	-
LLaVA-Video w/ AKS 2025.02	65.3	-	-	-	-	-	-
Weaver 2026.02	65.3	-	-	-	-	-	-
VideoChat-R1.5 2026.01	65.2	-	-	-	-	-	133
Long-VILA-R1 2026.02	65.1	-	-	-	-	-	-
LongVILA-R1 2026.01	65.1	-	-	-	-	-	-
BIMBA-LLaVA 2025.03	64.67	-	-	-	-	-	-
LLaVA-Video 2025.02	64.4	-	-	-	-	-	-
InternVL2.5 2026.02	64.2	-	-	-	-	-	-
VITAL 2026.01	64.1	-	-	-	-	-	-
Weaver-SFT 2026.02	63.8	-	-	-	-	-	-
Qwen2 VL (7B) 2024.10	63.3	-	-	-	-	-	-
Qwen2-VL 2025.03	63.3	-	-	-	-	-	-
LLaVA-Video 2025.03	63.3	-	-	-	-	-	-
Qwen2.5-VL 2026.02	63.3	-	-	-	-	-	-
LLaVA-Video-7B 2026.01	63.3	-	-	-	-	-	-
Video-RTS 2026.01	63	-	-	-	-	-	-
STTM 2026.01	62.6	-	-	-	-	-	-
Qwen2.5-VL-7B 2026.01	62.4	-	-	-	-	-	-
Video-R1 2026.01	61.8	-	-	-	-	-	386
Video-R1 2026.02	61.4	-	-	-	-	-	-
InfiniPot-V 2026.01	61.1	-	-	-	-	-	-
MiniCPM-V 2.6 2025.02	60.9	-	-	-	-	-	-
FrameMind 2026.02	60.9	-	-	-	-	-	-
VILA 2025.02	60.1	-	-	-	-	-	-
CoPE-VideoLM 2026.02	60.1	-	-	-	-	-	-
GPT 4V 2024.10	59.9	-	-	-	-	-	-
GPT-4V 2025.02	59.9	-	-	-	-	-	-
Qwen2-VL w/ AKS 2025.02	59.9	-	-	-	-	-	-
GPT4-V 2026.02	59.9	-	-	-	-	-	-
VideoRFT 2026.02	59.8	-	-	-	-	-	-
Video-RFT 2026.01	59.8	-	-	-	-	-	-
Video-R1-7B 2026.01	59.3	-	-	-	-	-	-
Video-MTR 2026.02	59	-	-	-	-	-	-
LLaVA-OV w/ AKS 2025.02	58.4	-	-	-	-	-	-
Baichuan-omni (7B) 2024.10	58.2	-	-	-	-	-	-
LLaVA-OneVision 2025.03	58.2	-	-	-	-	-	-
LLaVA-OneVision 2026.02	58.2	-	-	-	-	-	-
Qwen2-VL 2025.02	57.6	-	-	-	-	-	-
Temporal-RLT 2026.01	57.6	-	-	-	-	-	-
FastV 2026.02	57.5	-	-	-	-	-	-
DyCoke 2026.02	57.4	-	-	-	-	-	-
LLaVA-Scissor 2026.02	57.4	-	-	-	-	-	-
PLLaVA 2026.02	56.9	-	-	-	-	-	-
LLaVA-OV 2025.02	56.5	-	-	-	-	-	-
SmartSight 2026.01	56.2	-	-	-	-	-	-
VITA (8x7B) 2024.10	56.1	-	-	-	-	-	-
Kangaroo 2025.03	56	-	-	-	-	-	-
Video-XL 2025.03	55.5	-	-	-	-	-	-
Uniform 2026.01	54.7	-	-	-	-	-	-
MMViR (w/o text) 2026.01	54.7	-	-	-	-	-	-
LongVA 2025.03	54.3	-	-	-	-	-	-
VisionZip 2026.02	54.2	-	-	-	-	-	-
VideoTree 2026.01	53.1	-	-	-	-	-	-
MMViR 2026.01	51.7	-	-	-	-	-	-
BIMBA-LLAMA 2025.03	50.11	-	-	-	-	-	-
Random 2026.01	48.4	-	-	-	-	-	-
MMViR (w/o text) 2026.01	48.4	-	-	-	-	-	-
VideoChat2 2025.03	47.9	-	-	-	-	-	-
Video-LLaMA2 2025.03	47.9	-	-	-	-	-	-
LLaMA-3.2 (Video) 2025.03	47.31	-	-	-	-	-	-
MMViR 2026.01	46.9	-	-	-	-	-	-
VideoLLaMA 2 (7B) 2024.10	46.6	-	-	-	-	-	-
PLLAVA (LLaMA-3.2) 2025.03	46.56	-	-	-	-	-	-
LLaVA-NeXT-Video 2025.03	46.5	-	-	-	-	-	-
BIMBA-LLaVA 2025.03	45.66	-	-	-	-	-	-
PLLAVA 2025.03	44.25	-	-	-	-	-	-
LLaVA-NeXT (Video) 2025.03	42.21	-	-	-	-	-	-
MMViR (w/o img) 2026.01	42.2	-	-	-	-	-	-
MMViR (w/o img) 2026.01	42.2	-	-	-	-	-	-
PLLAVA 2025.03	42.13	-	-	-	-	-	-
Video-LLaVA 2025.03	40.4	-	-	-	-	-	-
Video-LLaVA (7B) 2024.10	39.9	-	-	-	-	-	-
VideoLLaVA 2025.02	39.9	-	-	-	-	-	-
MovieChat (2024) 2026.01	38.2	-	-	-	-	-	-
VideoChat2 (7B) 2024.10	33.7	-	-	-	-	-	-
LLaVA-NeXT-Video (7B) 2024.10	33.7	-	-	-	-	-	-
VideoRecap (2024) 2026.01	33.3	-	-	-	-	-	-
AnyGPT (8B) 2024.10	29.8	-	-	-	-	-	-
Hourvideo (2024) 2026.01	11.7	-	-	-	-	-	-
Video-LLaVA 2024.10	-	46.1	40.7	38.1	41.6	-	-

Showing 100 of 155 rows