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...

SpaceVista — leaderboard

Metric: Overall Accuracy (%). Source: peiwensun2000.github.io. 19 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro33.8
2GPT-533.7
3InternVL3-78B33.5
4Claude Sonnet 429.7
5GPT-4o26.9
6InternVL3-38B26.5
7Claude Opus 4.126.4
8Gemini 2.5 Flash24.4
9GLM-4.5V23.3

Interactive version: theaggregate.ai/benchmark?slug=spacevista · 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.