GapEval - Numerical Perception (Understanding): leaderboard

Metric: Accuracy (%; count two object types in an image and state the swapped counts; text answers to GapEval's bidirectional questions, judged correct or incorrect by GPT-5-mini against reference answers, mean of ten sampled runs). Source: arxiv.org. Saturation forecast: Around 2030. 15 models tracked.

Top models

#ModelScore
1GPT-5 Mini30.3
2Qwen 3 VL 235B A22B26
3Qwen 3 VL 8B25
4GPT-524.05
5Gemini 2.5 Flash17

Interactive version: theaggregate.ai/benchmark?slug=gapeval-numerical-perception-understanding · How It Works · Data refreshed daily, snapshot 2026-09-26.