OpenCodePapers

multimodal-reasoning-on-cv-bench

Visual ReasoningMultimodal Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models✓ Link90.0PhysBrain 1.5-8B2026-09-14
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching✓ Link88.82MJev-Spatial2026-10-15
MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling✓ Link86.73MV-STRIDE-SFT (Full-data SFT) (extra data)2026-09-08
ORBIT: Overcoming Hallucination Risks via Bi-manifold Interaction and Traction78.1ORBIT (Qwen2.5-VL-32B)2026-09-08
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space✓ Link77.66ProLaViT (Full)2026-07-03