DreamGen Bench componentBrowse 296

DreamGen Bench component

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

Version not specifiedExact reported variant
Agents6 ranked models6 reported values1 reportsHigher is better

Top rankings

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

6
RankModelBest scoreBest reported setting
1LVPExternal baseline0.889Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
2GigaWorldExternal baseline0.884Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
3Qwen-RobotWorldQwen0.832Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
4WowExternal baseline0.696Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
5VidarExternal baseline0.651Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source
6CosmosNVIDIA0.621Reported 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. This benchmark reports points rather than percent correct.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

DreamGen component scores; PA and IF are the source's position-aware and instruction-following measures.

Method / source