POINTS-Qwen2.5-7B: benchmark results
Provider: WeChat AI. Released 2024-11-18. Access: Open.
Aggregate Rating 1466 ± 34, rank #2962 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Human Object Interaction Recognition | 95 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Geometrical Perspective | 100 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - RR | 83.8 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Scene Emotion Recognition | 70 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Chart To Table | 100 | Score (%) | 97.3 |
| OpenVLM MMT-Bench - Traffic Light Understanding | 100 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - AUD | 67 | Score (%) | 96.1 |
| OpenVLM SEEDBench IMG - Visual Reasoning | 82.5 | Accuracy (%) | 95.8 |
| OpenVLM Q-Bench - What (Distortion) | 80 | Accuracy (%) | 95.6 |
| OpenVLM MMT-Bench - Counting By Visual Prompting | 50 | Score (%) | 95.4 |
| OpenVLM MMT-Bench - Gesture Recognition | 75 | Score (%) | 95.1 |
| OpenVLM MMT-Bench - TU | 50.6 | Score (%) | 94.7 |
Interactive version: theaggregate.ai/model?slug=points-qwen2-5-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.