Agentic MisalignmentBrowse 284 families
Agentic Misalignment
Can the model plan, use tools, and finish a multi-step task?
Version / measure
- Domain
- Agents
- Ranked models
- 5
- 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 | Gemini 3.1 ProGoogle | highcost n/a1 value · Jul 9 · source | 52.6% |
| 2 | Muse Spark 1.0Meta | reportedcost n/a1 value · Jul 9 · source | 47.7% |
| 3 | Muse Spark 1.1Meta | xhighcost n/a1 value · Jul 9 · source | 1.1% |
| 4 | Claude Opus 4.8Anthropic | maxcost n/a1 value · Jul 9 · source | 0.0% |
| 5 | GPT-5.5OpenAI | xhighcost n/a1 value · Jul 9 · source | 0.0% |
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. 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.
Method / source ↗