Playground (@withplayground) header
Playground (@withplayground) profile picture

Measuring the frontier of robot intelligence.

San Francisco, CA
Joined October 2026
Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)Photo by Playground (@withplayground)
Congrats @withplayground and @jonmayxyz on EFE-98! Excited to see sim rankings line up with real-robot rankings: 0.98 correlation with 21.5% of the Embodied First Exam’s tasks!
Introducing EFE-98: the most predictive public sim benchmark for real-robot performance. EFE-98 has the highest correlation (0.98, p < 0.01) with real-robot rankings of any benchmark we index. It uses just 21.5% of Embodied First Exam’s tasks and runs at a tenth of the cost.
1
3
18
1,096
Playground retweeted
LLMs scoring high on sim benchmarks is great, but they usually get privileged info not available in the real-world. The comparison I am excited to see are frontier LLMs vs. frontier WAMs on real-world benchmarks, run by third parties. The optimal solution is probably a mix of both. Either way, rising zero-shot generalization numbers move the whole field forward.
Yesterday, Fable 5.2 became the first frontier model release to include a robotics benchmark result (64.9% on RoboDojo Sim). The problem is that simulation benchmarks systematically underrate certain model architectures.
4
5
66
2,994
We’ve assembled a fleet of robots. This is just a part of it. Now we put the models to the test, in the real world. Coming online in 48 hours.
40
36
41
265
64,649
Playground retweeted
openai and google's models have been remarkably strong in robotics with gemini 4 argon's recent breakthrough scoring 87% on embodied reasoning and i'm sure openai wants a piece of the robotics market next year robots generate real-world sensory data that can improve future world models and physical intelligence so robots + next-gen LLMs make each other better
Introducing the Robot Intelligence Index: a unified ranking of robot models built from 16 public benchmarks. TL;DR: GPT-6 Astra dominates, taking #1 overall, #1 in precision, and #1 among the 12 models tested on multiple real-robot evals. 🧵
12
7
131
7,068