Skip to content
NewA calmer, faster ZeroHour

TuringSpace tests spatial reasoning with interactive CAPTCHAs

Original title: TuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAs

Hugging Face daily papersby Xuwei Ding, Skylar Zhai, Linxin Song ()1 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

Humans solve 94.1 percent; GPT-6 Astra fails 25.9 percent and Kimi K3 fails 68.0 percent.

TuringSpace is a synthetic web environment of 125 interactive CAPTCHAs covering five spatial abilities, solved by clicks and drags. Each task is a program that generates instances with a checker and an oracle, so the set can also train models. The authors say most failures come from misreading screenshots and that reasoning rarely corrects a wrong belief. Fine-tuning Qwen3.5-9B raised its success rate from 1.6 percent to 33.1 percent and improved seven out-of-distribution benchmarks. The environment will be released.

Unconfirmed: Benchmark scores and failure analysis are author-reported and not independently confirmed here.

Key facts
  • Best open-weight model Kimi K3 fails 68.0 percent of tasks.
  • Qwen3.5-9B rose from 1.6 percent to 33.1 percent success.
  • That fine-tune scored above Kimi K3.
  • VSI-Bench indoor videos gained 9.9 points.
  • Tasks span five spatial abilities and form a training gym.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Humans act in the visual world by inferring the 3D layout behind a 2D view, predicting how an action changes it, and correcting themselves after seeing the result. Can multimodal large language models (MLLMs) do the same? CAPTCHAs offer a natural test, since humans solve them through this very loop, clicking and dragging on the screen and adjusting after each result.

Hugging Face daily papers

By Xuwei Ding, Skylar Zhai, Linxin Song · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.