Hanging mug limited¶

Codex + GPT-6 Luna, reasoning xhigh (Azure OpenAI API, 2026-09-30 stress test)

← Task page · All RoboTwin 2.0 tasks in this run · Previous run, replaced by the rerun

ⓘ Note: rerun: the first trial lost its robot service, which crashed 7 times while starting (another user's job held half the GPU).

Model use: est. $0.250 at list price