OpenCodePapers

multimodal-reasoning-on-visulogic

Visual ReasoningMultimodal Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
STEP3-VL-10B Technical Report✓ Link32.7Step3-VL-10B (PaCoRe)2026-01-14
ERNIE 5.0 Technical Report32.0ERNIE 5.02026-02-04
LongCat-Next: Lexicalizing Modalities as Discrete Tokens✓ Link29.4LongCat-Next (A3B, 68.5B)2026-03-29
Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding✓ Link28.9VL-Cogito-7B with LEAD2026-03-09
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction28.6GAS (2B)2026-08-12
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models✓ Link27.7ReVision2026-02-02
LoopVL: Recurrent Visual Intelligence✓ Link27.0LoopVL-1B2026-09-29
MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning✓ Link26.9MetaphorStar-7B2026-02-11
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm26.4UVU 3B2026-06-03
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision✓ Link25.7Youtu-VL (4B)2026-01-27
Kwai Keye-VL Technical Report✓ Link25.6Keye-VL-8B2025-07-02
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs25.38Qwen3-VL-8B + PatternRL2026-08-17
Kwai Keye-VL 1.5 Technical Report✓ Link23.1Keye-VL-1.5-8B2025-09-01
VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision23.1VIVAS2026-09-08
Check out how to contribute new results. Then edit this file on GitLab or GitHub.