MARINER - Vessel Classification: leaderboard

Fine-grained vessel classification on MARINER (2026), a maritime vision benchmark of shore, shipboard, drone and open-source images with 63 vessel categories and adverse weather. Accuracy in percent; higher is better.

Metric: Accuracy (%) on MARINER fine-grained vessel classification (63 categories: 35 military, 27 civilian and Other; maritime images from shore, shipboard, UAV and open sources, including fog, ice, night and wave conditions); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4.183.3#505
2Gemini 2.5 Flash82.6#463
3GPT-4o80.5#751
4Qwen 2.5 VL 72B Instruct71.75#841
5Qwen 2.5 VL 32B Instruct65.8#1062
6InternVL3-78B65.67#759
7Qwen 2.5 VL 7B Instruct64.4#1902
8InternVL3-38B60.1#939
9LLaVA-OneVision-72B60#1771
10Qwen 2.5 VL 3B Instruct52.6#2713
11MiniCPM-V-2.649#3267
12Gemini 2.5 Pro42.1#276
13LLaVA-OneVision-7B41.2#2981
14InternVL3-8B41#1782
15InternVL2-8B26.3#3227

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mariner-vessel-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.