Multimodal Understanding on Seed-Bench (test)
66.9Overall ScoreInternLM-XComposer
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| InternLM-XComposerLanguage Model=InternLM-7B2023.09 | 66.9 | 65.2 | 75 | 71.7 | 67.6 | 60.8 | 56.2 | 55.3 | 74.4 | 77 | 48.5 | |
| LLaVA-1.5Language Model=LLaMA2-7B2023.09 | 66.2 | 61.8 | 74.3 | 69.9 | 67.6 | 60.3 | 57.2 | 50.8 | 63.9 | 77.3 | 35.3 | |
| Qwen-VL-ChatLanguage Model=Qwen-7B2023.09 | 65.4 | 61.9 | 73.3 | 67.3 | 69.6 | 57.7 | 52.9 | 48.2 | 59.8 | 74.6 | 53.5 | |
| InstructBLIP-VicunaLanguage Model=Vicuna-7B2023.09 | 58.8 | 52.2 | 60.2 | 58.9 | 65.6 | 43.6 | 57.2 | 40.3 | 52.6 | 47.7 | 43.5 | |
| Kosmos-2Language Model=Kosmos 1.3B2023.09 | 54.4 | 49.4 | 63.4 | 57.1 | 58.5 | 44 | 41.4 | 37.9 | 55.7 | 60.7 | 25.9 | |
| IDEFICS-80b-instructLanguage Model=LLaMA-65B2023.09 | 53.2 | 54.4 | 64 | 52.6 | 50.8 | 48.3 | 46.1 | 45.5 | 62.9 | 68 | 51.8 | |
| BLIP-2Language Model=Flan-T5-XL2023.09 | 49.7 | 45.7 | 59.1 | 53.9 | 49.2 | 42.3 | 43.2 | 36.7 | 55.7 | 45.6 | 25.9 | |
| MiniGPT-4Language Model=Vicuna-7B2023.09 | 47.4 | 42.6 | 56.3 | 49.2 | 45.8 | 37.9 | 45.3 | 32.6 | 47.4 | 57.1 | 11.8 | |
| OtterLanguage Model=MPT-7B2023.09 | 42.9 | 40.08 | 51.3 | 43.5 | 42.3 | 34.2 | 38.4 | 30.9 | 40.2 | 55.3 | 24.7 | |
| OpenFlamingoLanguage Model=MPT-7B2023.09 | 42.7 | 39.4 | 53.2 | 45.3 | 40 | 31.2 | 39.3 | 32.6 | 36.1 | 51.4 | 25.9 |