AgentWorldBenchBrowse 284 families
AgentWorldBench
Can the model plan, use tools, and finish a multi-step task?
Version / measure
- Domain
- Agents
- Ranked models
- 4
- Reported values
- 5
- 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 | Qwen-AgentWorld-397B-A17BQwen | reportedcost n/a1 value · Jun 22 · source | 58.71 |
| 2 | GPT-5.4OpenAI | reportedcost n/a1 value · Jun 22 · source | 58.25 |
| 3 | Qwen3.5-35B-A3BQwen | reportedcost n/a2 values · Jun 22 · source | 56.39 |
| 4 | Claude Sonnet 4.6Anthropic | reportedcost n/a1 value · Jun 22 · source | 56.04 |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarylimited 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.
Five-dimensional rubric mean across Qwen's seven-domain AgentWorldBench; Qwen states the 35B pipeline result as 47.73 → 56.39.
Method / source ↗