Expert-level Multimodal Understanding on MMMU-Pro
67.1AccuracyLaRe
Evaluation Results
| Method | Links | |
|---|---|---|
| LaReBase VLM=Qwen3-VL-8B-Instruct2025.11 | 67.1 | |
| ThymeBase VLM=Qwen3-VL-8B-Instruct2025.11 | 64.8 | |
| Qwen3-VL-8B-Thinking2025.11 | 60.4 | |
| LVRBase VLM=Qwen3-VL-8B-Instruct2025.11 | 60.1 | |
| Gemini2.5-Pro2025.11 | 59.6 | |
| CapImagineBase VLM=Qwen3-VL-8B-Instruct2025.11 | 59.4 | |
| Vision-R1Base VLM=Qwen3-VL-8B-Instruct2025.11 | 57.6 | |
| GPT-4o (0513)2025.06 | 51.9 | |
| Claude-3.5-Sonnet2025.06 | 51.5 | |
| InternVL3.5-8B2025.11 | 50.7 | |
| InternVL2.5-8B-GenRecalTeacher VLM=InternVL2.5-78B2025.06 | 48.8 | |
| InternVL2.5-78B2025.06 | 48.6 | |
| Gemini-1.5-Pro2025.06 | 46.9 | |
| Qwen2-VL-72B2025.06 | 46.2 | |
| InternVL2.5-8B-GenRecalTeacher VLM=Qwen2-VL-72B2025.06 | 43.8 | |
| InternVL2.5-8B-GenRecalTeacher VLM=InternVL2-76B2025.06 | 42.8 | |
| InternVL2-76B2025.06 | 40 | |
| Janus-pro-7B2025.11 | 38.1 | |
| InternVL2.5-8B-GenRecalTeacher VLM=NVLM-72B2025.06 | 34.7 | |
| LLaVA-OneVision-72B2025.06 | 31 |