BlueLM-V-3B: benchmark results
Provider: vivo. Released 2024-12-08.
Aggregate Rating 1499 ± 47, rank #2368 of 10916 rated models, from 434 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMBench V1.1 CN - Image Quality | 86.3 | Accuracy (%) | 100 |
| OpenVLM MMBench V1.1 EN - Image Quality | 93.5 | Accuracy (%) | 100 |
| OpenVLM MTVQA - French | 49.2 | Accuracy (%) | 100 |
| OpenVLM MTVQA - German | 45.3 | Accuracy (%) | 100 |
| OpenVLM MTVQA - Japanese | 24.2 | Accuracy (%) | 100 |
| OpenVLM Q-Bench - How (Distortion) | 69.3 | Accuracy (%) | 99.7 |
| OpenVLM MMBench V1.1 EN - CP | 86.5 | Accuracy (%) | 99.6 |
| OpenVLM MTVQA - Korean | 40.3 | Accuracy (%) | 99.4 |
| OpenVLM MMBench V1.1 CN - CP | 85.7 | Accuracy (%) | 99.3 |
| OpenVLM MMT-Bench - Chart To Text | 100 | Score (%) | 98.8 |
| OpenVLM MTVQA | 32.7 | Accuracy (%) | 98.7 |
| OpenVLM MMT-Bench - Age, Gender, and Race Recognition | 95 | Score (%) | 98.1 |
Interactive version: theaggregate.ai/model?slug=bluelm-v-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.