MathVista — leaderboard

MathVista evaluates mathematical reasoning over visual contexts, including figure QA, geometry, word problems, textbook QA, and visual QA.

Metric: Accuracy (%). Source: huggingface.co. Status: saturation imminent. 284 models tracked.

Top models

#ModelScore
1GPT-5 (2025-08-07)81.9
2Gemini 2.5 Pro80.9
3GPT-5 Mini (2025-08-07)79.2
4InternVL3-78B79
5Doubao-1.5-Pro78.6
6InternVL3-38B76.3
7InternVL3-14B74.4
8GPT-5 Nano73.1
9Ovis2-8B71.8
10GPT-4o ChatGPT71.6
11GPT-4.1 Mini70.9
12InternVL2.5-78B70.6
13InternVL3-8B70.5
14GPT-4.570.5
15Gemini 2.0 Flash70.4

Interactive version: theaggregate.ai/benchmark?slug=mathvista · How the rankings work · Data refreshed daily, snapshot 2026-07-22.