# Vals AI Robo-bench (Robo-bench)

> Tests agents controlling a simulated robot arm and humanoid through motor commands, sensor readings, and camera images.

Canonical page: https://benchlm.ai/benchmarks/robo-bench

- Category: [Agentic](/agentic)
- Last updated: October 13, 2026

Evaluation results published by [Vals AI](https://www.vals.ai/benchmarks/robo_bench). Published leaderboard aggregates and evaluation settings only. Dataset contents are not included.

## About Robo-bench

- Year: 2026
- Tasks: 24 simulated robot-control tasks
- Format: Mean task score out of 100
- Difficulty: Real-time perception, planning, and motor control
- Paper: [Robo-bench leaderboard and methodology](https://www.vals.ai/benchmarks/robo_bench)

Published scores average 24 tasks scored from 0 to 100: 13 arm tasks and 11 humanoid tasks. Each episode runs for three minutes in real time, including model deliberation. Models use their provider-specific coding agents at the highest supported reasoning setting. Results are display only and excluded from model rankings.

Robo-bench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (7 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | codex · max reasoning · codex | OpenAI | 28.33% |
| 2 | [GPT-6 Astra](/models/gpt-6-astra) | codex · max reasoning · codex | OpenAI | 23.33% |
| 3 | [Claude Opus 5.5](/models/claude-opus-5-5) | claude-code · max reasoning · claude-code | Anthropic | 14.58% |
| 4 | [Muse Wonder Full](/models/muse-wonder-full) | muse-code · max reasoning · muse-code | Meta | 10.42% |
| 5 | [Claude Fable 5.1](/models/claude-fable-5-1) | claude-code · max reasoning · claude-code | Anthropic | 5.83% |
| 6 | [Gemini 4 Argon](/models/gemini-4-argon) | antigravity · high reasoning · antigravity | Google | 0.83% |
| 7 | [Grok 4.7](/models/grok-4-7) | grok-build · xhigh reasoning · grok-build | xAI | 0.21% |

## FAQ

### What does Robo-bench measure?

Tests agents controlling a simulated robot arm and humanoid through motor commands, sensor readings, and camera images.

### Which model leads the published Robo-bench snapshot?

GPT-6.1 Sol currently leads the published Robo-bench snapshot with a score of 28.33%.

### How many models are evaluated on Robo-bench?

The October 13, 2026 contains 7 AI models.

### Does Robo-bench affect BenchLM's overall score?

Not directly. Robo-bench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.