Chat-UniVi-7B-v1.5: benchmark results
Provider: Other.
Aggregate Rating 1409 ± 43, rank #5683 of 10916 rated models, from 85 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EgoMonth - Spatial Relation | 56.9 | Accuracy (%; 51 spatial relation questions; four-option mult | 77.3 |
| OpenVLM Video - MLVU - Action Count | 30.6 | Accuracy (%) | 51.4 |
| OpenVLM Video - MVBench - Egocentric Navigation | 34.5 | Accuracy (%) | 51.4 |
| FluVid (Video Input) - PLCC | 0.49 | Pearson linear correlation (PLCC, -1 to 1) between the model | 50 |
| EgoMonth - Route Reasoning | 35.7 | Accuracy (%; 42 route reasoning questions; four-option multi | 40.9 |
| OpenVLM Video - MLVU - Anomaly Recognition | 64 | Accuracy (%) | 40.3 |
| OpenVLM Video - MVBench - Character Order | 53.5 | Accuracy (%) | 38.9 |
| OpenVLM Video - MMBench-Video - Hallucination | 0.4 | GPT-4 Rating (0-3) | 38.6 |
| FluVid (Video Input) | 0.48 | Spearman rank correlation (SRCC, -1 to 1) between the model' | 37.5 |
| EgoMonth - Event Time | 44.4 | Accuracy (%; 117 event time questions; four-option multiple- | 36.4 |
| EgoMonth - Object Counting | 33.3 | Accuracy (%; 57 object counting questions; four-option multi | 36.4 |
| OpenVLM Video - MVBench - Action Count | 42 | Accuracy (%) | 34.7 |
Interactive version: theaggregate.ai/model?slug=chat-univi-7b-v1-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.