POPE
AI benchmark results and model performance
Type: percentageMultimodal
Recorded results
3
Average score
85.93%
Score range
85.60% - 86.10%
Leading model
86.10% - Phi 3 Vision 128K Instruct
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Phi 3 Vision 128K Instruct | - | 86.10% | inferred family alias from phi-3.5-vision-instruct (score=0.3495; benches=9) | Yes | Source | |
| Phi 3.5 vision instruct | 23 Aug 2024 | 86.10% | - | Yes | Source | |
| Phi 4 multimodal instruct | 01 Feb 2025 | 85.60% | - | Yes | Source |
