InstructBLIP-Vicuna-7B: benchmark results
Provider: Salesforce. Released 2023-05-11. Access: Open.
Aggregate Rating 1273 ± 47, rank #8898 of 10489 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image only Conservation | 65.4 | Accuracy (%) | 86.8 |
| MMBench-Live - Attribute Reasoning | 91.73 | Accuracy (%; attribute reasoning questions; 5.9K newly gener | 80 |
| ProactiveBench - QuickDraw | 18.3 | Trajectory accuracy (%) on the partial QuickDraw sketches: m | 76.2 |
| ProactiveBench - ChangeIt | 24.5 | Trajectory accuracy (%) on the ambiguous ChangeIt video fram | 61.9 |
| MMBench-Live - Coarse Perception | 92.05 | Accuracy (%; coarse perception questions; 5.9K newly generat | 60 |
| ProactiveBench - MVP-N | 8.8 | Trajectory accuracy (%) on the uninformative multi-view obje | 57.1 |
| ChartBench - Chart Recognition | 49.57 | Acc+ (%) | 55 |
| ProactiveBench - COCO | 12.6 | Trajectory accuracy (%) on the MS-COCO scenes that need a ca | 47.6 |
| ProactiveBench - VSOD | 9.5 | Trajectory accuracy (%) on the temporally occluded video fra | 33.3 |
| ProactiveBench | 12.2 | Trajectory accuracy (%) averaged over the seven scenarios (R | 28.6 |
| CoreCognition Image only Spatiality | 42.99 | Accuracy (%) | 22.4 |
| GMAI-MMBench | 30.95 | Accuracy on single-choice questions (%) | 21.7 |
Interactive version: theaggregate.ai/model?slug=instructblip-vicuna-7b · How It Works · Data refreshed daily, snapshot 2026-11-20.