Research

Benchmark · 2026

OptoRigBench

13 models operate a simulated neuroscience microscope with planted faults; 64 of 195 sessions pass.

micro1 Eval Hackathon, Nov 2026Viewer ↗Dataset ↗
Robotics · 2026

behavior26

Soltanalipour, Le

The paired A/B difference is +0.019 (95% CI [−0.091, +0.128], p = 0.73), so the progress head made no measurable difference on this task.

2026 BEHAVIOR Challenge, standard trackWeights ↗