Multimodal Question Answering on MM-Vet (test)
70.3AccuracyGPT4-V + UnAC
Evaluation results
| Method | Links | |
|---|---|---|
| GPT4-V + UnACBackbone=GPT4-V, Prompting Strategy=UnAC2026.05 | 70.3 | |
| GPT4-V + SKETCHPADBackbone=GPT4-V, Prompting Strategy=SKETCHPAD2026.05 | 69.3 | |
| GPT4-V + CCoTBackbone=GPT4-V, Prompting Strategy=CCoT2026.05 | 67.7 | |
| GPT4-VBackbone=GPT4-V, Prompting Strategy=Baseline2026.05 | 67.2 | |
| GPT4-V + SoMBackbone=GPT4-V, Prompting Strategy=SoM2026.05 | 66 | |
| Gemini-1.5-flash + UnACBackbone=Gemini-1.5-flash, Prompting Strategy=UnAC2026.05 | 64.9 | |
| InternVL2.0-8B + UnACBackbone=InternVL2.0-8B, Prompting Strategy=UnAC2026.05 | 63.3 | |
| Gemini-1.5-flashBackbone=Gemini-1.5-flash, Prompting Strategy=Baseline2026.05 | 62.2 | |
| LLaVA-OneVision-7B + UnACBackbone=LLaVA-OneVision-7B, Prompting Strategy=UnAC2026.05 | 60.2 | |
| InternVL2.0-8BBackbone=InternVL2.0-8B, Prompting Strategy=Baseline2026.05 | 60 | |
| LLaVA-OneVision-7BBackbone=LLaVA-OneVision-7B, Prompting Strategy=Baseline2026.05 | 57.5 | |
| LLaVA-v1.6-7B + UnACBackbone=LLaVA-v1.6-7B, Prompting Strategy=UnAC2026.05 | 48.5 | |
| LLaVA-v1.6-7BBackbone=LLaVA-v1.6-7B, Prompting Strategy=Baseline2026.05 | 47.5 |