MARINER - VQA OCR-Integrated QA: 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 questions that need text read from the ship; higher is better.
Metric: Accuracy (%) on MARINER maritime visual question answering (ship text questions; multiple-choice questions generated from verified image metadata and audited by maritime annotators); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | MiniCPM-V-2.6 | 91.58 | #3311 |
| 2 | InternVL3-78B | 90.1 | #765 |
| 3 | InternVL3-38B | 89.85 | #948 |
| 4 | LLaVA-OneVision-72B | 89.85 | #1782 |
| 5 | Qwen 2.5 VL 32B Instruct | 89.11 | #1065 |
| 6 | Qwen 2.5 VL 72B Instruct | 88.86 | #849 |
| 7 | Qwen 2.5 VL 7B Instruct | 88.61 | #1919 |
| 8 | InternVL2-8B | 88.61 | #3268 |
| 9 | InternVL3-8B | 87.38 | #1795 |
| 10 | Gemini 2.5 Pro | 86.39 | #280 |
| 11 | Qwen 2.5 VL 3B Instruct | 85.89 | #2720 |
| 12 | GPT-4.1 | 84.16 | #506 |
| 13 | LLaVA-OneVision-7B | 83.17 | #3002 |
| 14 | GPT-4o | 78.22 | #754 |
| 15 | LLaVA-v1.5-7B | 66.58 | #7642 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mariner-vqa-ocr-integrated-qa · How It Works · Data refreshed daily, snapshot 2026-11-22.