Ivy-VL-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1389 ± 27, rank #6548 of 10916 rated models, from 545 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MEGA-Bench Task - SNLI-VE Visual Entailment | 100 | Task Score (%) | 100 |
| MEGA-Bench Task - MMSoc HatefulMemes | 85.7 | Task Score (%) | 97.7 |
| MEGA-Bench Task - Paper Review Acceptance | 60 | Task Score (%) | 96.5 |
| MEGA-Bench Task - Egocentric Spatial Reasoning | 66.7 | Task Score (%) | 91.9 |
| MEGA-Bench Task - Face Keypoint Detection | 84.9 | Task Score (%) | 91.9 |
| MEGA-Bench Task - Red Teaming Visual Order A | 90.5 | Task Score (%) | 90.7 |
| MEGA-Bench Task - AV Human Multiview Counting | 26.7 | Task Score (%) | 88.4 |
| MEGA-Bench Task - Visual Prediction Rater Openable Part Segmentation | 28.6 | Task Score (%) | 87.2 |
| MEGA-Bench Task - Autorater Unmask | 64.3 | Task Score (%) | 86 |
| MEGA-Bench Task - CLEVRER Moving Direction Video | 37.5 | Task Score (%) | 86 |
| MEGA-Bench Task - Graph Hamiltonian Path | 41.1 | Task Score (%) | 84.9 |
| MEGA-Bench Task - GUI Act Mobile Tap | 35.7 | Task Score (%) | 83.7 |
Interactive version: theaggregate.ai/model?slug=ivy-vl-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.