MIOH - Counting: leaderboard

Metric: Accuracy (%; counting questions about how many objects there are across several images; multi-image questions built from COCO-ReM, PACO and Visual Genome scenes in three reasoning patterns (comprehensive, comparative, selective), averaged over the easy, hard-negative, hard-positive and eight-image conditions). Source: arxiv.org. Saturation forecast: Around September 2027. 29 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro57.5
2GPT-549.1
3MiniCPM-V-2.628.3
4Qwen 2.5 VL 7B28
5InternVL3.5-8B27.6
6Qwen 2 VL 7B26
7Phi-4 Multimodal Instruct24
8Qwen 2 VL 2B21.2

Interactive version: theaggregate.ai/benchmark?slug=mioh-counting · How It Works · Data refreshed daily, snapshot 2026-09-29.