Mantis-8B-Fuyu: benchmark results
Provider: Salesforce. Released 2024-05-29. Access: Open.
Aggregate Rating 1192 ± 49, rank #9658 of 10916 rated models, from 443 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MME - Scene | 171.2 | Score | 99.1 |
| OpenVLM MMT-Bench - Spot The Diff | 95 | Score (%) | 97.3 |
| OpenVLM A-Bench - Nouns as Adjectives | 86 | Accuracy (%) | 97.2 |
| OpenVLM MMT-Bench - MIA | 82.5 | Score (%) | 97.1 |
| OpenVLM MMT-Bench - Color Constancy | 71.4 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 45 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Depth Estimation | 80 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Rotated Object Detection | 66.7 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - VI | 64 | Score (%) | 87.4 |
| OpenVLM MMT-Bench - Color Contrast | 70 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Raven Progressive Matrices | 25 | Score (%) | 85.2 |
| OpenVLM MMT-Bench - Waste Recognition | 100 | Score (%) | 84.5 |
Interactive version: theaggregate.ai/model?slug=mantis-8b-fuyu · How It Works · Data refreshed daily, snapshot 2026-11-08.