Skip to content
The Aggregate

Unified LLM rankings, daily

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

SpatialGen-Bench (Text Answering) — leaderboard

Metric: Overall Accuracy (%). Source: zju-omniai.github.io. 25 models tracked.

Top models

#ModelScore
1Claude Fable 581.26
2GPT-5.6 Sol80.98
3Kimi K363.36
4Claude Opus 4.857.79
5GPT-5.456.24
6InternVL3.5-8B33.11

Interactive version: theaggregate.ai/benchmark?slug=spatialgen-bench-text-answering · How It Works · Data refreshed daily, snapshot 2026-07-27.

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