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

Open-ended Question-Answering on Vad-Reasoning-Plus

0.106BLEU-3

Qwen3VL-Thinking

Updated 4d ago

Evaluation Results

Method	Links
Qwen3VL-Thinking 2026.01		0.106	0.008	0.044
Vad-R1-Plus 2026.01		0.03	0.019	0.078
Vad-R1 2026.01		0.023	0.013	0.058
Gemini2.5-Flash 2026.01		0.019	0.01	0.05
LLaVA-OneVision 2026.01		0.017	0.009	0.049
Grok4-Fast 2026.01		0.015	0.009	0.043
Holmes-VAU 2026.01		0.014	0.008	0.045
Kimi-VL-Thinking 2026.01		0.013	0.007	0.038
Qwen3VL-Instruct 2026.01		0.012	0.006	0.036
Kimi-VL-Instruct 2026.01		0.011	0.006	0.035
OpenR1-Video 2026.01		0.011	0.006	0.039
VideoChat-R1 2026.01		0.011	0.006	0.037
MiniCPM-V4.5 2026.01		0.011	0.005	0.037
InternVL3.5 2026.01		0.009	0.005	0.031
Ovis2.5 2026.01		0.009	0.004	0.032
VideoChat-Flash 2026.01		0.008	0.004	0.029
GPT5-mini 2026.01		0.005	0.002	0.026
Video-XL 2026.01		0.004	0.002	0.013
Video-R1 2026.01		0.004	0.002	0.01
Keye-VL1.5 2026.01		0.004	0.002	0.022
MiMo-VL 2026.01		0.004	0.002	0.019
HAWK 2026.01		0.004	0.002	0.019
VideoLLaMA3 2026.01		0.003	0.002	0.014
InternVideo2.5 2026.01		0.002	0.001	0.01
LLaVA-NeXT-Video 2026.01		0.002	0.001	0.009
Holmes-VAD 2026.01		0.002	0.001	0.009
GLM4.1-V 2026.01		0.001	0	0.008