Mini-InternVL-Chat-2B-V1.5: benchmark results
Provider: Shanghai AI Lab. Released 2024-04-28. Access: Open.
Aggregate Rating 1335 ± 36, rank #8076 of 10916 rated models, from 433 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - VI | 65.6 | Score (%) | 92.5 |
| OpenVLM MMT-Bench - Micro Expression Recognition | 40 | Score (%) | 89.8 |
| OpenVLM MMT-Bench - Geometrical Relativity | 70 | Score (%) | 87.9 |
| OpenVLM MMT-Bench - Single Object Tracking | 65 | Score (%) | 87.6 |
| OpenVLM MMT-Bench - Video Captioning | 100 | Score (%) | 87.4 |
| OpenVLM MMT-Bench - Color Contrast | 70 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Traffic Sign Understanding | 90 | Score (%) | 86.2 |
| OpenVLM MMT-Bench - Color Assimilation | 70 | Score (%) | 85 |
| OpenVLM MMT-Bench - Action Quality Assessment | 30 | Score (%) | 84.7 |
| OpenVLM CCBench - Food and Clothes | 63.5 | Accuracy (%) | 84.1 |
| OpenVLM MMT-Bench - Vehicle Keypoint Detection | 66.7 | Score (%) | 83.3 |
Interactive version: theaggregate.ai/model?slug=mini-internvl-chat-2b-v1-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.