Slime-8B: benchmark results
Provider: UCAS. Released 2024-10-29. Access: Open.
Aggregate Rating 1298 ± 40, rank #8771 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Sports Recognition | 100 | Score (%) | 98.5 |
| OpenVLM A-Bench - Nouns as Adjectives | 86 | Accuracy (%) | 97.2 |
| OpenVLM MME - Color | 190 | Score | 93.4 |
| OpenVLM MMT-Bench - Gaze Estimation | 35 | Score (%) | 93 |
| OpenVLM MMT-Bench - Geometrical Perspective | 83.3 | Score (%) | 90.5 |
| OpenVLM MMT-Bench - Image Matting | 30 | Score (%) | 90.3 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 70 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Geometrical Relativity | 70 | Score (%) | 87.9 |
| OpenVLM MMT-Bench - Social Relation Recognition | 65 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Counting By Category | 38.8 | Score (%) | 85.4 |
| OpenVLM MMT-Bench - VI | 63.1 | Score (%) | 85.4 |
| OpenVLM MMT-Bench - Action Quality Assessment | 30 | Score (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=slime-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.