InternVL3-8B
OpenGVLab · 2025-04-11 · 7.9B parameters
InternVL3-8B is OpenGVLab's 7.94B-parameter multimodal checkpoint, combining an InternViT-300M vision encoder, a two-layer MLP projector, and a Qwen2.5-7B language backbone. Released on April 11, 2025 after native multimodal pre-training, supervised fine-tuning, and mixed preference optimization, it accepts text, image, and video within a 32,768-token context; its weights are Apache-2.0 licensed while the surrounding InternVL project code is MIT licensed.
Benchmark scores
| Benchmark | Score |
|---|---|
| AI2D (OpenVLM) | 85.1 |
| Capability | 123.7 |
| CharXiv Reasoning | 37.6 |
| CharXiv-D | 73.6 |
| HallusionBench (OpenVLM) | 49.0 |
| MATH-Vision | 29.0 |
| MathVista (OpenVLM) | 70.5 |
| MM-Vet (OpenVLM) | 82.8 |
| MMMU Validation (OpenVLM) | 62.2 |
| MMStar (OpenVLM) | 68.7 |