InternVL2-8B-MPO-CoT: benchmark results
Provider: Shanghai AI Lab. Released 2024-11-14. Access: Open.
Aggregate Rating 1472 ± 35, rank #2800 of 10916 rated models, from 433 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Sign Language Recognition | 55 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Image Dense Captioning | 84.2 | Score (%) | 98.5 |
| OpenVLM MMT-Bench - Age, Gender, and Race Recognition | 95 | Score (%) | 98.1 |
| OpenVLM MME - Text Translation | 200 | Score | 97 |
| OpenVLM MME - Count | 180 | Score | 96.4 |
| OpenVLM CCBench - Calligraphy and Painting | 87.7 | Accuracy (%) | 94.7 |
| OpenVLM MMT-Bench - Chemical Apparatus Recognition | 75 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| OpenVLM MMMU - Clinical Medicine | 73.3 | Accuracy (%) | 94.5 |
| OpenVLM MMT-Bench - Facial Expression Recognition | 75 | Score (%) | 94.4 |
| OpenVLM MMT-Bench - Humanities and Social Science | 72.7 | Score (%) | 93.9 |
| OpenVLM MMT-Bench - Salient Object Detection RGBD | 60 | Score (%) | 93.4 |
Interactive version: theaggregate.ai/model?slug=internvl2-8b-mpo-cot · How It Works · Data refreshed daily, snapshot 2026-11-08.