EBench success rateBrowse 296

EBench success rate

Can the model plan, use tools, and finish a multi-step task?

Version not specifiedExact reported variant
Agents5 ranked models6 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

5
RankModelBest scoreBest reported setting
1Qwen-RobotManipQwen29.9%Reported configurationQwen report2 values · 1 reportJun 15, 2026 · source
2π₀.₅Physical Intelligence18.1%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
3InternVLA-A1External baseline17.9%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
4π₀Physical Intelligence17.0%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
5X-VLAExternal baseline6.2%Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
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.

EBench reports success rate (SR) and a separate task score for each split.

Method / source