Manipulation benchmarkBrowse 284 families
Manipulation benchmark
Can the model plan, use tools, and finish a multi-step task?
Version / measure
- Domain
- Agents
- Ranked models
- 2
- Reported values
- 2
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | ABot-M0External baseline | reportedcost n/a1 value · May 29 · source | 98.6% |
| 2 | Qwen-VLA-InstructQwen | reportedcost n/a1 value · May 29 · source | 97.9% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model plan, use tools, and finish a multi-step task?
Agentic execution across tools, environments, or long-running workflows. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Qwen-VLA-Instruct unified manipulation table; specialist baseline cells are retained exactly where printed.
Method / source ↗