Taiyi: benchmark results
Provider: Other. Access: API.
Aggregate Rating 1568 ± 35, rank #1427 of 10916 rated models, from 438 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI2D | 90.8 | Accuracy (%) | 99.7 |
| OpenVLM AI2D - Food Chains and Webs | 98.9 | Accuracy (%) | 99.6 |
| OpenVLM AI2D - Life Cycles | 90.4 | Accuracy (%) | 99.6 |
| OpenVLM MMT-Bench - Geometrical Perspective | 100 | Score (%) | 99.5 |
| OpenVLM AI2D - Solar System | 100 | Accuracy (%) | 99.3 |
| OpenVLM AI2D - Types Of | 87.5 | Accuracy (%) | 99.3 |
| OpenVLM MMBench V1.0 EN - CP | 89.1 | Accuracy (%) | 99.3 |
| OpenVLM MMT-Bench - Behavior Anomaly Detection | 80 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - LVLM Response Judgement | 70 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Scene Graph Recognition | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - IEJ | 67.5 | Score (%) | 99 |
| OpenVLM MMBench V1.1 CN - Physical Property Reasoning | 82.3 | Accuracy (%) | 98.9 |
Interactive version: theaggregate.ai/model?slug=taiyi · How It Works · Data refreshed daily, snapshot 2026-11-08.