Egocentric Visual Question Answering on EGOPOINTVQA (test)
75.6Reference AccuracyGPT-5
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GPT-5Size=-, LLM=-2026.03 | 75.6 | 53.6 | 62.3 | 50 | 56.1 | 77.8 | 62.6 | |
| HINT_InternVL3-8BSize=8B, LLM=InternLM32026.03 | 75 | 66.1 | 64.9 | 35.4 | 61 | 79.8 | 63.7 | |
| HINT_InternVL3-14BSize=14B, LLM=InternLM32026.03 | 73.8 | 69.6 | 64.9 | 54.2 | 63.4 | 82.5 | 68.1 | |
| InternVL3Size=78B, LLM=InternLM32026.03 | 71.4 | 71.4 | 62.3 | 45.8 | 68.3 | 80.1 | 66.6 | |
| InternVL3Size=38B, LLM=InternLM32026.03 | 70.2 | 67.9 | 65.8 | 45.8 | 65.9 | 78.9 | 65.8 | |
| EgoGPTSize=7B, LLM=Qwen22026.03 | 67.3 | 46.4 | 50.9 | 47.9 | 48.8 | 74.1 | 55.9 | |
| InternVL3Size=8B, LLM=InternLM32026.03 | 66.1 | 57.5 | 63.2 | 33.3 | 51.3 | 76.8 | 58 | |
| ViSpeakSize=7B, LLM=Qwen22026.03 | 65.5 | 42.9 | 48.2 | 39.6 | 51.2 | 70.2 | 52.9 | |
| Qwen3-VLSize=32B, LLM=Qwen32026.03 | 63.7 | 67.9 | 65.8 | 66.7 | 63.4 | 77.2 | 67.5 | |
| InternVL3Size=14B, LLM=InternLM32026.03 | 63.1 | 66.1 | 61.4 | 50 | 58.5 | 77.2 | 62.7 | |
| Qwen3-VLSize=8B, LLM=Qwen32026.03 | 61.9 | 53.6 | 56.1 | 35.4 | 48.8 | 79.4 | 55.9 | |
| InternVL2.5Size=38B, LLM=InternLM2.52026.03 | 61.3 | 57.1 | 60.5 | 39.6 | 63.4 | 77.2 | 59.9 | |
| LLaVA-OneVisionSize=72B, LLM=Qwen22026.03 | 61.3 | 44.6 | 60.5 | 41.7 | 51.2 | 72.3 | 55.3 | |
| HINT_LLaVA-OneVisionSize=7B, LLM=Qwen22026.03 | 60.7 | 50 | 56.1 | 39.6 | 48.8 | 71.1 | 54.4 | |
| VGLLM-QASize=8B, LLM=Qwen2.52026.03 | 57.7 | 35.7 | 53.5 | 39.6 | 36.6 | 70.2 | 48.9 | |
| GPT-4oSize=-, LLM=-2026.03 | 56.1 | 29.5 | 43.1 | 44.8 | 41.5 | 65.7 | 46.8 | |
| InternVL2.5Size=8B, LLM=InternLM2.52026.03 | 54.2 | 41.1 | 59.6 | 37.5 | 63.4 | 77.2 | 55.5 | |
| LLaVA-OneVisionSize=7B, LLM=Qwen22026.03 | 54.2 | 42.9 | 53.5 | 35.4 | 46.3 | 67.1 | 49.9 | |
| RandomSize=-, LLM=-2026.03 | 20 | 20 | 27 | 20 | 20 | 50 | 26.2 |