MARINER - VQA Perspective Estimation: leaderboard
Maritime visual question answering on MARINER (2026), with multiple-choice questions built from verified image metadata and audited by maritime annotators. Accuracy in percent on vessel perspective questions; higher is better.
Metric: Accuracy (%) on MARINER maritime visual question answering (vessel perspective questions; multiple-choice questions generated from verified image metadata and audited by maritime annotators); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 72.73 | #505 |
| 2 | Gemini 2.5 Pro | 68.53 | #276 |
| 3 | GPT-4o | 62.7 | #751 |
| 4 | Gemini 2.5 Flash | 59.67 | #463 |
| 5 | LLaVA-OneVision-72B | 57.34 | #1771 |
| 6 | InternVL3-78B | 56.41 | #759 |
| 7 | Qwen 2.5 VL 72B Instruct | 56.18 | #841 |
| 8 | InternVL3-38B | 55.94 | #939 |
| 9 | Qwen 2.5 VL 7B Instruct | 51.52 | #1902 |
| 10 | InternVL3-8B | 50.58 | #1782 |
| 11 | Qwen 2.5 VL 32B Instruct | 49.65 | #1062 |
| 12 | MiniCPM-V-2.6 | 44.29 | #3267 |
| 13 | LLaVA-OneVision-7B | 41.96 | #2981 |
| 14 | InternVL2-8B | 41.72 | #3227 |
| 15 | Qwen 2.5 VL 3B Instruct | 39.16 | #2713 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mariner-vqa-perspective-estimation · How It Works · Data refreshed daily, snapshot 2026-11-21.