LaViSA: leaderboard
Structural ambiguity arises when a single sentence admits multiple valid interpretations due to its syntactic structure, posing a fundamental challenge for language understanding. Visual scenes serve as useful cues for resolving such ambiguity, and Vision and Language Models (VLMs) need to be capable of deriving possible semantic interpretations from visual scenes. We introduce Language and Vision
Metric: PT-Acc (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 88.9 | #58 |
| 2 | Gemini 3.1 Flash Lite | 84 | #191 |
| 3 | GPT-5.2 | 83.4 | #110 |
| 4 | Gemma 3 27B | 71.7 | #607 |
| 5 | Gemma 3 12B | 69.9 | #671 |
| 6 | Gemma 3 4B | 51 | #1089 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=lavisa · How It Works · Data refreshed daily, snapshot 2026-10-20.