XVERSE-V-13B: benchmark results
Provider: XVERSE. Released 2024-04-28. Access: Open.
Aggregate Rating 1354 ± 35, rank #7597 of 10916 rated models, from 399 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Action Quality Assessment | 40 | Score (%) | 97.1 |
| OpenVLM MME - Scene | 165.8 | Score | 91.7 |
| OpenVLM COCO Captions | 45.3 | CIDEr | 91 |
| OpenVLM MME - Count | 173.3 | Score | 86.8 |
| OpenVLM MMBench V1.1 CN - Identity Reasoning | 98.7 | Accuracy (%) | 86.6 |
| OpenVLM MMMU - Diagnostics and Laboratory Medicine | 46.7 | Accuracy (%) | 82.3 |
| OpenVLM SEEDBench IMG - Text Understanding | 70.2 | Accuracy (%) | 82.2 |
| OpenVLM MMBench V1.0 CN - CP | 86.5 | Accuracy (%) | 81.9 |
| OpenVLM MMBench V1.1 CN - Image Emotion | 82.2 | Accuracy (%) | 77 |
| OpenVLM MMBench V1.1 EN - Image Emotion | 80 | Accuracy (%) | 76 |
| OpenVLM MMMU - Mechanical Engineering | 43.3 | Accuracy (%) | 71.6 |
| OpenVLM MME - Landmark | 171 | Score | 70.5 |
Interactive version: theaggregate.ai/model?slug=xverse-v-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.