List your company

Video Question Answering on RAVEN-QA Hard Queries

96.8AccuracyVLM Only
-1.37624.11249.675.088Jun 23, 2026

Evaluation results

MethodLinks
VLM OnlyVLM=Gp32026.0696.8
RAVENEmbedder=Seed1.6-Embed, VLM=Gp32026.0695.1
RAVENEmbedder=QQMM-v2, VLM=Gp32026.0692.7
RAVENEmbedder=SigLIP, VLM=Gp32026.0685.4
VLM OnlyVLM=GPT-4o2026.0685.4
RAVENEmbedder=Seed1.6-Embed, VLM=GPT-52026.0682.9
RAVENEmbedder=QQMM-v2, VLM=Gp2.52026.0682.9
RAVENEmbedder=QQMM-v2, VLM=Gf2.52026.0682.9
RAVENEmbedder=QQMM-v2, VLM=GPT-52026.0682.9
RAVENEmbedder=CLIP-B, VLM=Gp32026.0682.9
VLM OnlyVLM=Gp2.52026.0682.9
RAVENEmbedder=Seed1.6-Embed, VLM=Gf2.52026.0680.5
RAVENEmbedder=SigLIP, VLM=Gp2.52026.0680.5
RAVENEmbedder=SigLIP, VLM=GPT-52026.0680.5
VLM OnlyVLM=GPT-52026.0680.5
RAVENEmbedder=Seed1.6-Embed, VLM=Gp2.52026.0678
VLM OnlyVLM=Gf2.52026.0678
RAVENEmbedder=Seed1.6-Embed, VLM=GPT-4o2026.0673.2
RAVENEmbedder=QQMM-v2, VLM=GPT-4o2026.0673.2
RAVENEmbedder=SigLIP, VLM=GPT-4o2026.0673.2
RAVENEmbedder=CLIP-B, VLM=GPT-52026.0673.2
RAVENEmbedder=SigLIP, VLM=Gf2.52026.0668.3
Caption (4o-mini)VLM=Gp32026.0668.3
RAVENEmbedder=Seed1.6-Embed, VLM=Embedder Only2026.0663.4
RAVENEmbedder=QQMM-v2, VLM=Embedder Only2026.0663.4
RAVENEmbedder=CLIP-B, VLM=Gp2.52026.0663.4
Caption (4o-mini)VLM=Q3-32b2026.0663.4
RAVENEmbedder=SigLIP, VLM=Embedder Only2026.0661
Caption (4o-mini)VLM=GPT-52026.0661
RAVENEmbedder=Seed1.6-Embed, VLM=Q3-32b2026.0658.5
Caption (4o-mini)VLM=Gp2.52026.0658.5
Caption (4o-mini)VLM=Gf2.52026.0658.5
RAVENEmbedder=SigLIP, VLM=Gm3-27b2026.0656.1
RAVENEmbedder=CLIP-B, VLM=Gf2.52026.0656.1
RAVENEmbedder=CLIP-B, VLM=GPT-4o2026.0656.1
Caption (4o-mini)VLM=GPT-4o2026.0656.1
RAVENEmbedder=Seed1.6-Embed, VLM=Gm3-27b2026.0653.7
RAVENEmbedder=Seed1.6-Embed, VLM=Q2.5-32b2026.0651.2
RAVENEmbedder=QQMM-v2, VLM=Gm3-27b2026.0651.2
RAVENEmbedder=QQMM-v2, VLM=Q3-32b2026.0648.8
RAVENEmbedder=SigLIP, VLM=Q2.5-32b2026.0648.8
RAVENEmbedder=QQMM-v2, VLM=Q2.5-32b2026.0646.3
RAVENEmbedder=CLIP-B, VLM=Gm3-27b2026.0646.3
RAVENEmbedder=QQMM-v2, VLM=Gm3-12b2026.0643.9
RAVENEmbedder=SigLIP, VLM=Gm3-12b2026.0643.9
RAVENEmbedder=SigLIP, VLM=Q3-32b2026.0641.5
Caption (4o-mini)VLM=Q2.5-32b2026.0641.5
RAVENEmbedder=CLIP-B, VLM=Embedder Only2026.0639
VLM OnlyVLM=Q2.5-32b2026.0636.6
RAVENEmbedder=Seed1.6-Embed, VLM=Gm3-12b2026.0634.1
RAVENEmbedder=CLIP-B, VLM=Q3-32b2026.0634.1
RAVENEmbedder=CLIP-B, VLM=Q2.5-32b2026.0626.8
RAVENEmbedder=CLIP-B, VLM=Gm3-12b2026.0624.4
VLM OnlyVLM=Gm3-27b2026.0624.4
Caption (4o-mini)VLM=Gm3-27b2026.0622
VLM OnlyVLM=Gm3-12b2026.0619.5
Caption (4o-mini)VLM=Gm3-12b2026.0617.1
Caption (4o-mini)VLM=Q2.5-7b2026.0617.1
VLM OnlyVLM=Q3-32b2026.0614.6
VLM OnlyVLM=Q2.5-7b2026.067.3
RAVENEmbedder=Seed1.6-Embed, VLM=Q2.5-7b2026.064.9
RAVENEmbedder=QQMM-v2, VLM=Q2.5-7b2026.062.4
RAVENEmbedder=SigLIP, VLM=Q2.5-7b2026.062.4
RAVENEmbedder=CLIP-B, VLM=Q2.5-7b2026.062.4