Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Open LMM Reasoning - MathVista — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.

Top models

#ModelScore
1InternVL3-78B79
2Doubao-1.5-Pro78.6
3SenseNova78.4
4InternVL2.5-78B-MPO76.6
5InternVL3-38B76.3
6Ovis2-34B76.1
7MUG-U-7B74.8
8Step-1o74.7
9InternVL3-14B74.4
10Qwen2.5-VL-72B74.2

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

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.