POINTS1.5-Qwen2.5-7B: benchmark results
Provider: WeChat AI. Released 2024-12-06. Access: Open.
Aggregate Rating 1494 ± 20, rank #2443 of 10916 rated models, from 518 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - AUD | 71 | Score (%) | 100 |
| OpenVLM MMT-Bench - Multiple View Image Understanding | 55 | Score (%) | 100 |
| Open LMM Reasoning - MathVision - topology | 39.1 | Accuracy (%) | 98 |
| OpenVLM MMT-Bench - Handwritten Mathematical Expression Recognition | 100 | Score (%) | 97.8 |
| OpenVLM A-Bench - Minor Object Recognition | 100 | Accuracy (%) | 97.5 |
| OpenVLM A-Bench - Contradiction Overcome | 91.7 | Accuracy (%) | 96.9 |
| OpenVLM MMBench V1.1 CN - Attribute Recognition | 96.6 | Accuracy (%) | 96.5 |
| OpenVLM MMT-Bench - Traffic Light Understanding | 100 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - Clothes Keypoint Detection | 80 | Score (%) | 95.9 |
| OpenVLM MMT-Bench - Face Detection | 85 | Score (%) | 95.9 |
| OpenVLM MMT-Bench - Human Object Interaction Recognition | 90 | Score (%) | 95.6 |
| OpenVLM MMT-Bench - Counting By Visual Prompting | 50 | Score (%) | 95.4 |
Interactive version: theaggregate.ai/model?slug=points1-5-qwen2-5-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.