MARINER - VQA Civilian Equipment Grounding: 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 civilian equipment grounding questions; higher is better.

Metric: Accuracy (%) on MARINER maritime visual question answering (civilian equipment grounding questions; multiple-choice questions generated from verified image metadata and audited by maritime annotators); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4.185.07#505
2Gemini 2.5 Pro84.18#276
3InternVL3-38B82.09#939
4InternVL3-78B81.49#759
5GPT-4o81.19#751
6InternVL3-8B77.01#1782
7Qwen 2.5 VL 32B Instruct74.63#1062
8Qwen 2.5 VL 7B Instruct73.73#1902
9LLaVA-OneVision-72B73.43#1771
10Qwen 2.5 VL 72B Instruct72.54#841
11Gemini 2.5 Flash68.96#463
12MiniCPM-V-2.668.06#3267
13LLaVA-OneVision-7B67.16#2981
14InternVL2-8B64.48#3227
15Qwen 2.5 VL 3B Instruct60#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-civilian-equipment-grounding · How It Works · Data refreshed daily, snapshot 2026-11-21.