WetLabs Benchmark tests robots in science labs across 9 tasks; Astra leads
philhchen · x · 2026-09-26
Mecka's team released the WetLabs Benchmark, testing whether robots are ready to accelerate science labs: 9 critical wet-lab tasks from easy to hard, with 3 leading models given 20 attempts each. Astra leads, but comes close—step-function improvements in latest models like Astra/Opus-5.5 make such benchmarks increasingly important.
Related event: WetLabs Benchmark Tests Whether Robots Can Speed Up Lab Science(2 posts)→
More from Embodied
- Meta's new VR glasses land but still trail Vision Pro, longtime reviewer says — adariostrange · 2026-09-26
- Dual Covariance Gaussian Splatting SLAM decouples rendering and registration — kwangmoo_yi · 2026-09-26
- Meta goes all-in on Muse: voice, glasses, a charm — and a free rootable cloud PC per user — altryne · 2026-09-26
- WetLabs Benchmark tests robots on 9 wet-lab tasks: can machines accelerate science? — ericjang11 · 2026-09-26
- Arm Total Design: the build pipeline from virtual robot to real fleet, 83 partners — lmoroney · 2026-09-26
- Robot arm collective builds 0.5mm-precision wood model to plan grain-aware clock milling — CatAstro_Piyush · 2026-09-26