Long screwdriver · spin vertical¶
Agent runs
Each mode of this task runs once per run. Est. cost is tokens at list price (data/prices.yml), never a bill; see the DexToolBench runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✗ 1h 00m 0% | 09-29 03:29 | 1h 00m | — | 7.5M / 122k | $0.159 | grader_error 0, missing_trajectory 1 |
| L✗ 1h 00m 0% | 09-29 12:09 | 1h 00m | — | 18.2M / 120k | $0.267 | deterministic 1, grader_error 0, video_rendered 1 |
1 other run(s) of DexToolBench
Codex + GPT-6 Luna, reasoning xhigh (Azure OpenAI API, 2026-09-30 stress test)
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✗ 1h 00m 0% ⓘ | 10-01 03:43 | 1h 00m | — | 21.9M / 273k | $0.403 | grader_error 0, missing_trajectory 1 |
| L✗ 1h 00m 0% | 09-30 12:47 | 1h 00m | — | 23.0M / 129k | $0.312 | deterministic 1, grader_error 0, video_rendered 1 |
Task instruction (upstream)
Pick up the long screwdriver and move it through the demonstrated motion (spinning it about a vertical axis): bring it to each of the 100 goal poses in order.
Recorded by us: SimToolReal's pretrained RL policy replayed in our MuJoCo port of the task, four views (front, side / top, oblique); it reaches 27 of 100 goals here. The green ghost tool is the current goal.
What DexToolBench states about this task
| Defined in | dextoolbench/trajectories/screwdriver/long_screwdriver/spin_vertical.json |
| Category | screwdriver |
| Object | long_screwdriver |
| Task | spin_vertical |
| N Goals | 100 |
| Tool Model | assets/urdf/dextoolbench/screwdriver/long_screwdriver/long_screwdriver.urdf |
| Table | table_narrow.urdf (plain) |
| Metric | task progress: goals reached / goals (8 grasp-box keypoints within 1.5 cm; 10 s per goal) |
From https://github.com/tylerlum/simtoolreal @ 313d5ae.
Measured on the stack we run — MuJoCo 3.3.7 (CPU, bit-exact replay), KUKA iiwa 14 (MuJoCo Menagerie 1b86ece) + Sharpa HA4, 600 Hz physics, 60 Hz control
| Harness Task | dextoolbench_screwdriver_long_screwdriver_spin_vertical |
| Oracle | SimToolReal's pretrained policy, recorded in this scene and replayed: 27/100 goals |
Read from run in our MuJoCo port (robot_coding_bench tasks/dextoolbench_screwdriver_long_screwdriver_spin_vertical, image rcb-mujoco 0.1.1), 2026-09-28.
Tags¶
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.