| Introducing Gemini 3.8 Flash and 3.8 Flash Cyber | ✓ Link | 86.2 | Gemini 3.8 Flash | 2026-09-02 |
| dots3-note Preview: A Small but Mighty Step Toward Long-Horizon Agency in Real Life | ✓ Link | 83.1 | dots3-note Preview | 2026-08-13 |
| Kimi K2.6 | ✓ Link | 80.4 | Kimi K2.6 | 2026-04-20 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 79.5 | Qwen3.5-27B | 2026-02-16 |
| Muse Glimmer 30B: An On-Device Agentic Model | ✓ Link | 78.8 | Muse Glimmer-30B (High Reasoning) | 2026-10-17 |
| Introducing OpenAI o3 and o4-mini | ✓ Link | 78.6 | OpenAI o3 | 2025-04-16 |
| Qwen3.6 | ✓ Link | 78.4 | Qwen3.6-27B | 2026-04-21 |
| Qwen3.6 | ✓ Link | 78.0 | Qwen3.6-35B-A3B | 2026-04-21 |
| Kimi K2.5: Visual Agentic Intelligence | ✓ Link | 77.5 | Kimi K2.5 | 2026-02-02 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 77.5 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 77.2 | Qwen3.5-122B-A10B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 73.0 | Qwen3.5-9B | 2026-02-16 |
| Qwen3.5-Omni Technical Report | | 72.5 | Qwen3.5-Omni-Plus | 2026-04-21 |
| EXAONE 4.5 Technical Report | ✓ Link | 71.7 | EXAONE 4.5 (Reasoning) | 2026-04-09 |
| Qwen3-VL Technical Report | ✓ Link | 66.1 | Qwen3-VL-235B-A22B-Thinking | 2025-11-26 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 63.6 | Nemotron 3 Nano Omni (Reasoning) | 2026-04-27 |
| LongCat-Next: Lexicalizing Modalities as Discrete Tokens | ✓ Link | 60.1 | LongCat-Next (A3B, 68.5B) | 2026-03-29 |
| STEP3-VL-10B Technical Report | ✓ Link | 59.52 | Step3-VL-10B | 2026-01-14 |
| Twin-T & TwintVQA: A Reliable Structure-Detail Separating VLM and a Comprehensive Benchmark for Chart and Table Tasks | ✓ Link | 57.1 | Twin-T-7B | 2026-06-03 |
| V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning | ✓ Link | 57.0 | V-Rubrics (+ GRPO) (extra data) | 2026-08-26 |
| Multimodal OCR: Parse Anything from Documents | ✓ Link | 55.3 | dots.mocr | 2026-03-13 |
| Introducing OpenAI o1 | | 55.1 | OpenAI o1 | 2024-09-12 |
| Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models | ✓ Link | 54.1 | Metis | 2026-04-09 |
| OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks | ✓ Link | 53.0 | OpenVLThinkerV2 (Ours) | 2026-04-09 |
| Command A+ | | 52.7 | Command A+ | 2026-05-20 |
| Qwen2.5-VL Technical Report | ✓ Link | 49.7 | Qwen2.5-VL-72B | 2025-02-19 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 46.4 | Penguin-VL 8B | 2026-03-06 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 46.0 | InternVL3-78B | 2025-04-14 |
| A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone | | 45.4 | MiniCPM-V 4.6-Thinking (16x) | 2026-05-13 |
| Language-guided Frequency Modulation for Large Vision-Language Models | | 44.7 | LFM (w/ Qwen2.5-VL) | 2026-06-03 |
| Step-GUI Technical Report | ✓ Link | 44.6 | Step-GUI-8B | 2025-12-17 |
| Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision | ✓ Link | 44.0 | Youtu-VL (4B) | 2026-01-27 |
| Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction | | 40.5 | GAS (4B) | 2026-08-12 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 35.6 | LLaDA-UI (pre-training) | 2026-09-09 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 26.8 | Penguin-VL 2B | 2026-03-06 |