LabOSBench - Measurement Configuration: leaderboard
Measurement-configuration operations in LabOSBench (Zou et al., 2026), such as setting accelerating voltage, magnification, scan size and rate, gains, angles, temperatures and pulse parameters before acquisition, across its web-based scientific-instrument simulators. Each subtask starts from its canonical pre-state with a 50-step budget and runs twice; the score is the percent of successful runs averaged over the category's subtasks; higher is better.
Metric: Subtask Success Rate (%; mean over the category's operation-level subtasks, 2 runs each). Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 81.5 | #48 |
| 2 | Seed-1.6 | 66.7 | #447 |
| 3 | Claude Sonnet 4.5 | 63 | #244 |
| 4 | Claude Opus 4.5 | 63 | #152 |
| 5 | Kimi K2.5 | 53.7 | #252 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=labosbench-measurement-configuration · How It Works · Data refreshed daily, snapshot 2026-11-12.