| Ovis2.5 Technical Report | ✓ Link | 91.2 | Ovis2.5-9B | 2025-08-15 |
| PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding | ✓ Link | 86.5 | PLM-8B | 2025-04-17 |
| Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding | ✓ Link | 85.7 | Molmo2-8B | 2026-01-15 |
| NVIDIA Nemotron Nano V2 VL | ✓ Link | 85.4 | Nemotron Nano V2 VL (Reasoning off) (extra data) | 2025-11-06 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 85.1 | Nemotron 3 Nano Omni | 2026-04-27 |
| Qwen2.5-VL Technical Report | ✓ Link | 84.9 | Qwen2.5-VL-7B | 2025-02-19 |
| The Llama 3 Herd of Models | ✓ Link | 84.8 | Llama 3-V (405B) | 2024-07-31 |
| Qwen2.5-Omni Technical Report | ✓ Link | 84.4 | Qwen2.5-Omni-7B | 2025-03-26 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 84.3 | InternVL3-78B | 2025-04-14 |
| Qwen2.5-VL Technical Report | ✓ Link | 83.5 | Qwen2.5-VL-72B | 2025-02-19 |
| Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models | ✓ Link | 83.1 | Molmo 72B | 2024-09-25 |
| Gemini: A Family of Highly Capable Multimodal Models | ✓ Link | 82.3 | Gemini Ultra | 2023-12-19 |
| Aria: An Open Multimodal Native Mixture-of-Experts Model | ✓ Link | 81.1 | Aria | 2024-10-08 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context | ✓ Link | 78.7 | Gemini 1.5 Pro | 2024-03-08 |
| InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models | ✓ Link | 78.5 | InfiniteVL-Base (extra data) | 2025-12-09 |
| GPT-4 Technical Report | ✓ Link | 78.0 | GPT-4 (vision, 0-shot) | 2023-03-15 |
| MiniCPM-V: A GPT-4V Level MLLM on Your Phone | ✓ Link | 76.6 | MiniCPM-Llama3-V 2.5 | 2024-08-03 |
| PaliGemma 2: A Family of Versatile VLMs for Transfer | ✓ Link | 76.6 | PaliGemma 2 10B | 2024-12-04 |
| Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid | ✓ Link | 76.0 | Mini-Monkey (extra data) | 2024-08-04 |
| Building and better understanding vision-language models: insights and future directions | ✓ Link | 74.9 | Idefics3-8B | 2024-08-22 |
| ZAYA1-VL-8B Technical Report | ✓ Link | 74.4 | ZAYA1-VL-8B | 2026-05-08 |
| What matters when building vision-language models? | ✓ Link | 73.0 | Idefics2 (w/ image split) | 2024-05-03 |
| Multimodal Autoregressive Pre-training of Large Vision Encoders | ✓ Link | 58.2 | AIMv2 ViT-3B/14 + Llama 3.0 8B | 2024-11-21 |
| Video-LLaVA: Learning United Visual Representation by Alignment Before Projection | ✓ Link | 51.8 | Video-LLaVA-7B | 2023-11-16 |