InternVL2-8B-MPO: benchmark results
Provider: Shanghai AI Lab. Released 2024-11-14. Access: Open.
Aggregate Rating 1437 ± 21, rank #4317 of 10916 rated models, from 517 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Pixel Localization | 60 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Chemical Apparatus Recognition | 80 | Score (%) | 99 |
| OpenVLM MMT-Bench - Age, Gender, and Race Recognition | 95 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Temporal Ordering | 45 | Score (%) | 97.6 |
| OpenVLM MMT-Bench - Sign Language Recognition | 50 | Score (%) | 96.8 |
| OpenVLM MME - Count | 180 | Score | 96.4 |
| OpenVLM MMT-Bench - Image Dense Captioning | 78.9 | Score (%) | 96.1 |
| OpenVLM CCBench - Calligraphy and Painting | 87.7 | Accuracy (%) | 94.7 |
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| OpenVLM CCBench - Traditional Shows | 78.8 | Accuracy (%) | 94.5 |
| OpenVLM MMT-Bench - Action Quality Assessment | 35 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Humanities and Social Science | 72.7 | Score (%) | 93.9 |
Interactive version: theaggregate.ai/model?slug=internvl2-8b-mpo · How It Works · Data refreshed daily, snapshot 2026-11-08.