LLaVA-InternLM2-20B (QLoRA): benchmark results
Provider: LLaVA Team. Released 2024-03-05. Access: Open.
Aggregate Rating 1327 ± 37, rank #8216 of 10916 rated models, from 404 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Human Object Interaction Recognition | 95 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Micro Expression Recognition | 55 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 85 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Depth Estimation | 85 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Emo | 60 | Score (%) | 96.4 |
| OpenVLM MMBench V1.1 EN - Image Topic | 98.9 | Accuracy (%) | 95.2 |
| OpenVLM MMT-Bench - Relation Hallucination | 85 | Score (%) | 93.9 |
| OpenVLM MMBench V1.1 EN - Image Scene | 91 | Accuracy (%) | 93.5 |
| OpenVLM MMT-Bench - One Shot Detection | 85 | Score (%) | 92.7 |
| OpenVLM MMT-Bench - Attribute Hallucination | 85 | Score (%) | 92.5 |
| OpenVLM MMT-Bench - CIM | 71.7 | Score (%) | 92.2 |
| OpenVLM MMT-Bench - 3D | 55 | Score (%) | 90.8 |
Interactive version: theaggregate.ai/model?slug=llava-internlm2-20b-qlora · How It Works · Data refreshed daily, snapshot 2026-11-08.