Benchmark Almanac

Pantograph frontier-LLM robot benchmark (Pandroid)

GPT-6 Astra 36.3%
Not in model cards

GPT-6 Astra and Claude Fable 5.1 drive Pandroid robots through a fixed tool harness on eight simple manipulation tasks, 10 blind-graded attempts each.

Controlled design: same prompt, tools and budget (20 min or 96 turns), random interleaving across six robots, blind grading, p about 0.001 stratified by task. Astra 35%, Fable 15%. Human teleoperators reach 100%. Fixed clock penalizes slow thinking. One team runs both models.

Made by
Pantograph PBC
Released
September 2026
Kind
Real robots
Level
Everyday
Scored
Graded by people
Answers
Agent task
Tasks
Kept private
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
September 2026
Scores refreshed
November 12th, 2026
2
Models scored on its own leaderboard

GPT-6 Astra leads with 36.3%

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 36.3 GPT-6 Astra
  2. 15.0 Claude Fable 5.1
  1. 1 GPT-6 Astra low; 20 minutes or 96 turns 36.3%
  2. 2 Claude Fable 5.1 low; 20 minutes or 96 turns 15%

Source: Official Pantograph frontier-LLM robot benchmark (Pandroid) leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 36.3% low; 20 minutes or 96 turns, Pantograph Pandroid Sep 2026 Official leaderboard
2 Claude Fable 5.1 15% low; 20 minutes or 96 turns, Pantograph Pandroid Sep 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Astra Claude Fable 5.1

Source: Official Pantograph frontier-LLM robot benchmark (Pandroid) leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Robotics

All 103 in Robotics
  • ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy. Gemini Robotics ER 2 78.5%
  • RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 29%
  • RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. FLUX 3 Action 42.9%
  • Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
  • Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%
  • Moment finding (Google DeepMind) In use Models find the moment in a robot video when an event happens. Scored by accuracy and mean absolute time distance in seconds. Gemini Robotics ER 2 91.3%