AKI-4B: benchmark results
Provider: Other.
Aggregate Rating 1273 ± 37, rank #9034 of 10916 rated models, from 442 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - MeViS | 60 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Deepfake Detection | 70 | Score (%) | 98.3 |
| OpenVLM MMT-Bench - MIA | 82.5 | Score (%) | 97.1 |
| OpenVLM A-Bench - Contradiction Overcome | 91.7 | Accuracy (%) | 96.9 |
| OpenVLM MMT-Bench - Geometrical Relativity | 75 | Score (%) | 96.1 |
| OpenVLM MMBench V1.1 EN - Image Topic | 98.9 | Accuracy (%) | 95.2 |
| OpenVLM MMT-Bench - Animals Recognition | 100 | Score (%) | 94.9 |
| OpenVLM MMT-Bench - Spot The Diff | 85 | Score (%) | 92.7 |
| OpenVLM COCO Captions | 57.3 | CIDEr | 91.4 |
| OpenVLM MMT-Bench - Body Emotion Recognition | 55 | Score (%) | 89.6 |
| OpenVLM MMBench V1.1 EN - Image Emotion | 82.2 | Accuracy (%) | 88.7 |
| OpenVLM MMT-Bench - Image Season Recognition | 85 | Score (%) | 86.9 |
Interactive version: theaggregate.ai/model?slug=aki-4b · How It Works · Data refreshed daily, snapshot 2026-11-08.