AMVICC - MMVP Individual Accuracy - Orientation and Direction: leaderboard
Metric: Individual accuracy (%; the 30 MMVP questions on 15 image pairs in the Orientation and Direction category, free-form answers graded by GPT-4 against the authors' rubric). Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.2 90B Vision Instruct | 90 |
| 2 | Gemini 2.5 Pro | 86.67 |
| 3 | Llama 4 Maverick | 86.67 |
| 4 | GPT-4o | 83.33 |
| 5 | Claude Opus 4.1 | 83.33 |
| 6 | Qwen 2.5 VL 72B Instruct | 73.33 |
| 7 | Llama 4 Scout | 70 |
| 8 | Gemma 3 27B | 66.67 |
| 9 | pixtral-large-2411 | 66.67 |
| 10 | Claude Sonnet 4 | 60 |
| 11 | Grok 4 | 40 |
Interactive version: theaggregate.ai/benchmark?slug=amvicc-mmvp-individual-accuracy-orientation-and-direction · How It Works · Data refreshed daily, snapshot 2026-09-29.