LabRobFail-Bench - Failure Detection: leaderboard
LabRobFail-Bench (Dalian University of Technology and collaborators, 2026) tests robot failure analysis in simulated chemical self-driving laboratories, where control, physics and semantic failures are injected into manipulation videos. This task asks whether the trajectory contains a failure at all. Top-1 accuracy in percent on the seen-environment test split, higher is better.
Metric: Top-1 accuracy (%; binary detection of whether the trajectory contains a failure; robot-manipulation videos from simulated chemical self-driving laboratories with injected control, physics and semantic failures, seen-environment test split; answers from simulator ground truth; zero-shot VLM). Source: arxiv.org. Saturation forecast: Around October 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 57.13 | #453 |
| 2 | Gemini 2.0 Flash | 56.85 | #704 |
| 3 | GPT-5.4 | 52.34 | #123 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=labrobfail-bench-failure-detection · How It Works · Data refreshed daily, snapshot 2026-11-13.