POINTS-Yi-1.5-9B: benchmark results
Provider: WeChat AI. Released 2024-08-27. Access: Open.
Aggregate Rating 1452 ± 36, rank #3686 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM Q-Bench - How (Others) | 80 | Accuracy (%) | 100 |
| OpenVLM MME - Position | 173.3 | Score | 97.9 |
| OpenVLM MMT-Bench - Web Shopping | 60 | Score (%) | 97.3 |
| OpenVLM MMT-Bench - Google Apps | 60 | Score (%) | 96.6 |
| OpenVLM MMT-Bench - Salient Object Detection RGB | 75 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Depth Estimation | 80 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - General Action Recognition | 100 | Score (%) | 93.4 |
| OpenVLM MMT-Bench - One Shot Detection | 85 | Score (%) | 92.7 |
| OpenVLM MMT-Bench - GN | 50 | Score (%) | 92.5 |
| OpenVLM MMT-Bench - Traffic Participants Understanding | 65 | Score (%) | 92.5 |
| OpenVLM MMT-Bench - Age, Gender, and Race Recognition | 90 | Score (%) | 91.3 |
| OpenVLM MMT-Bench - Temporal Anticipation | 80 | Score (%) | 91.3 |
Interactive version: theaggregate.ai/model?slug=points-yi-1-5-9b · How It Works · Data refreshed daily, snapshot 2026-11-08.