Critique on VISCO 1.0 (test)
86.5VISCoreHuman
Evaluation Results
| Method | Links | |
|---|---|---|
| HumanSize=N/A2024.12 | 86.5 | |
| GPT-4oSize=Unknown2024.12 | 52.4 | |
| Claude-3.5-SonnetSize=Unknown2024.12 | 51.3 | |
| Gemini-1.5-ProSize=Unknown2024.12 | 45 | |
| LLaVA-CriticSize=72B2024.12 | 42.6 | |
| Qwen2-VLSize=72B2024.12 | 37.4 | |
| Llama-3.2Size=90B2024.12 | 36.4 | |
| MolmoSize=72B2024.12 | 35.6 | |
| LLaVA-OVSize=72B2024.12 | 35.3 | |
| NVLMSize=72B2024.12 | 33.1 | |
| InternVL2Size=40B2024.12 | 28.5 | |
| InternVL2Size=76B2024.12 | 26.4 | |
| InternVL2Size=26B2024.12 | 25.2 | |
| InternVL2Size=8B2024.12 | 23.3 | |
| LLaVA-v1.6Size=7B2024.12 | 21.8 | |
| Qwen2-VLSize=7B2024.12 | 21.7 | |
| LLaVA-v1.6Size=13B2024.12 | 21 | |
| LLaVA-CriticSize=7B2024.12 | 20 | |
| Prometheus-VisionSize=13B2024.12 | 19.3 | |
| Prometheus-VisionSize=7B2024.12 | 17.7 | |
| MolmoSize=7B2024.12 | 13.4 | |
| MiniCPM-V2.6Size=8B2024.12 | 13.1 | |
| Llama-3.2Size=11B2024.12 | 11.4 | |
| LLaVA-v1.6Size=34B2024.12 | 11.1 | |
| DeepSeek-VLSize=7B2024.12 | 7.5 | |
| LLaVA-OVSize=7B2024.12 | 7.5 |