AMVICC - MMVP Pair Accuracy - Positional and Relational Context: leaderboard
Metric: Pair accuracy (%; the 16 MMVP image pairs in the Positional and Relational Context category, a pair credited only when both of its questions are answered correctly; free-form answers graded by GPT-4 against the authors' rubric). Source: arxiv.org. Saturation forecast: Around 2030. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.2 90B Vision Instruct | 81.25 |
| 2 | Claude Opus 4.1 | 62.5 |
| 3 | Gemini 2.5 Pro | 56.25 |
| 4 | GPT-4o | 56.25 |
| 5 | Llama 4 Maverick | 56.25 |
| 6 | Claude Sonnet 4 | 50 |
| 7 | Llama 4 Scout | 50 |
| 8 | Qwen 2.5 VL 72B Instruct | 50 |
| 9 | Gemma 3 27B | 43.75 |
| 10 | pixtral-large-2411 | 43.75 |
| 11 | Grok 4 | 25 |
Interactive version: theaggregate.ai/benchmark?slug=amvicc-mmvp-pair-accuracy-positional-and-relational-context · How It Works · Data refreshed daily, snapshot 2026-09-29.