DreamGen Bench
Can the model plan, use tools, and finish a multi-step task?
Agents6 ranked models6 reported values1 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | Qwen-RobotWorldQwen | 4.952 | Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source |
| 2 | LVPExternal baseline | 4.758 | Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source |
| 3 | WowExternal baseline | 4.728 | Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source |
| 4 | GigaWorldExternal baseline | 4.216 | Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source |
| 5 | CosmosNVIDIA | 4.129 | Reported configurationQwen report1 value · 1 reportJun 15, 2026 · source |
| 6 | VidarExternal baseline | 3.341 | 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.
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 source-defined aggregate across six component metrics.
Method / source