Image Captioning Evaluation on CaptionQA
89.96GPT ScoreVISE
Evaluation Results
| Method | Links | |
|---|---|---|
| VISEModel Scale=32B2026.06 | 89.96 | |
| VisionZero-CLEVRModel Scale=32B2026.06 | 89.74 | |
| VisionZero-ChartModel Scale=32B2026.06 | 89.69 | |
| iReasonerModel Scale=32B2026.06 | 89.66 | |
| EvoLMMModel Scale=32B2026.06 | 89.58 | |
| VisionZero-RWModel Scale=32B2026.06 | 89.09 | |
| VisPlayModel Scale=32B2026.06 | 89.04 | |
| BaseModel Scale=32B2026.06 | 88.96 | |
| VISEModel Scale=8B2026.06 | 86.35 | |
| VisionZero-CLEVRModel Scale=8B2026.06 | 86.01 | |
| VisionZero-ChartModel Scale=8B2026.06 | 85.96 | |
| iReasonerModel Scale=8B2026.06 | 85.89 | |
| EvoLMMModel Scale=8B2026.06 | 85.82 | |
| VisionZero-RWModel Scale=8B2026.06 | 85.38 | |
| VisPlayModel Scale=8B2026.06 | 85.32 | |
| BaseModel Scale=8B2026.06 | 85.21 | |
| VISEModel Scale=4B2026.06 | 85.19 | |
| VisPlayModel Scale=4B2026.06 | 84.16 | |
| VisionZero-ChartModel Scale=4B2026.06 | 83.9 | |
| VisionZero-CLEVRModel Scale=4B2026.06 | 83.89 | |
| iReasonerModel Scale=4B2026.06 | 83.52 | |
| EvoLMMModel Scale=4B2026.06 | 83.41 | |
| VisionZero-RWModel Scale=4B2026.06 | 83.1 | |
| BaseModel Scale=4B2026.06 | 82.93 | |
| VISEModel Scale=2B2026.06 | 79.16 | |
| VisionZero-CLEVRModel Scale=2B2026.06 | 77.69 | |
| VisPlayModel Scale=2B2026.06 | 77.35 | |
| BaseModel Scale=2B2026.06 | 77.04 | |
| iReasonerModel Scale=2B2026.06 | 76.82 | |
| EvoLMMModel Scale=2B2026.06 | 76.73 | |
| VisionZero-RWModel Scale=2B2026.06 | 76.69 | |
| VisionZero-ChartModel Scale=2B2026.06 | 76.54 |