GLM-4V-Plus: benchmark results
Provider: Zhipu. Access: API.
Aggregate Rating 1566 ± 17, rank #1464 of 10916 rated models, from 468 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MME - Color | 200 | Score | 100 |
| OpenVLM MMT-Bench - Art Design | 100 | Score (%) | 100 |
| OpenVLM MMT-Bench - Font Recognition | 55 | Score (%) | 99 |
| OpenVLM MMT-Bench - Order Hallucination | 65 | Score (%) | 99 |
| OpenVLM MMMU - Math | 73.3 | Accuracy (%) | 98.8 |
| OpenVLM AI2D - Parts of the Earth | 88.5 | Accuracy (%) | 98.4 |
| OpenVLM SEED-Bench 2 Plus - Charts | 70.9 | Accuracy (%) | 98.3 |
| OpenVLM MMT-Bench - HLN | 78.7 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - MeViS | 55 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Astronomical Recognition | 100 | Score (%) | 97.8 |
| OpenVLM MMT-Bench - DU | 87.9 | Score (%) | 97.8 |
| OpenVLM SEEDBench IMG - Text Understanding | 79.8 | Accuracy (%) | 97.8 |
Interactive version: theaggregate.ai/model?slug=glm-4v-plus · How It Works · Data refreshed daily, snapshot 2026-11-08.