Moondream1: benchmark results
Provider: vikhyatk. Released 2024-01-19. Access: Open.
Aggregate Rating 1196 ± 47, rank #9643 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Micro Expression Recognition | 50 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Color Contrast | 80 | Score (%) | 95.9 |
| OpenVLM MMT-Bench - Logo and Brand Recognition | 100 | Score (%) | 94.4 |
| OpenVLM COCO Captions | 70 | CIDEr | 94.3 |
| OpenVLM MMT-Bench - Deepfake Detection | 65 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Temporal Ordering | 40 | Score (%) | 92 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 70 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Geometrical Relativity | 70 | Score (%) | 87.9 |
| OpenVLM MMT-Bench - VI | 64.2 | Score (%) | 87.9 |
| OpenVLM MMT-Bench - Color Assimilation | 70 | Score (%) | 85 |
| OpenVLM MMT-Bench - 3D | 52.5 | Score (%) | 83.7 |
| OpenVLM MMT-Bench - 3D Indoor Recognition | 40 | Score (%) | 82.5 |
Interactive version: theaggregate.ai/model?slug=moondream1 · How It Works · Data refreshed daily, snapshot 2026-11-08.