GQA: leaderboard
GQA: Evaluates multimodal understanding across image, text, chart, diagram, or cross-modal reasoning tasks.
Metric: Overall Accuracy (%). Source: cs.stanford.edu. Source: eval.ai. 543 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Molmo2-8B | 87.07 | #543 |
Interactive version: theaggregate.ai/benchmark?slug=gqa · How It Works · Data refreshed daily, snapshot 2026-10-20.