Image Captioning on Flickr30k (val)
62.3CIDErBYE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BYELVLM=InternVL2026.06 | 62.3 | 76.3 | |
| BYORnLVLM=LLaVA2026.06 | 62 | 0 | |
| BYORn-FLVLM=InternVL2026.06 | 60.8 | 0.6 | |
| SFTLVLM=Qwen-VL2026.06 | 60.7 | 100 | |
| ONIONLVLM=Qwen-VL2026.06 | 60.6 | 51 | |
| ONIONLVLM=InternVL2026.06 | 57.9 | 50.9 | |
| BYELVLM=Qwen-VL2026.06 | 57.7 | 99.8 | |
| SFTLVLM=InternVL2026.06 | 57.3 | 99.8 | |
| BYORnLVLM=InternVL2026.06 | 56 | 0.8 | |
| BYELVLM=LLaVA2026.06 | 54.7 | 62.4 | |
| BYORn-FLVLM=Qwen-VL2026.06 | 52.2 | 0.9 | |
| BYORnLVLM=Qwen-VL2026.06 | 52.2 | 2.1 | |
| SFTLVLM=LLaVA2026.06 | 51.4 | 57.3 | |
| ONIONLVLM=LLaVA2026.06 | 51.3 | 23 | |
| BYORn-FLVLM=LLaVA2026.06 | 42.4 | 0.3 | |
| ONIONLVLM=Otter2026.06 | 41.2 | 52.8 | |
| SFTLVLM=Otter2026.06 | 40.6 | 99.8 | |
| BYELVLM=Otter2026.06 | 40.6 | 100 | |
| BYORn-FLVLM=Otter2026.06 | 39.9 | 0 | |
| BYORnLVLM=Otter2026.06 | 38.5 | 0 |