AutomationBenchBrowse 296

AutomationBench

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

Latest stableAnthropic launch table · September 2026 · task revision not printed
Agents4 ranked models4 reported values1 reportsHigher is better

Top rankings

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

4
RankModelBest scoreBest reported setting
1Claude Fable 5.1Anthropic31.4%Reported configurationAnthropic report1 value · 1 reportSep 1, 2026 · source
2Claude Opus 5Anthropic26.9%Reported configurationAnthropic report1 value · 1 reportSep 1, 2026 · source
3GPT-5.6 SolOpenAI19.6%Reported configurationAnthropic report1 value · 1 reportSep 1, 2026 · source
4Claude Fable 5Anthropic17.1%Reported configurationAnthropic report1 value · 1 reportSep 1, 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.

The launch table does not print a task-set revision or cost-per-task series. Anthropic states that production safeguards were enabled for these comparisons; safeguard interventions can lower scores and intervention cases can be scored as zero. The launch table does not print a task-set revision or cost-per-task series.

Method / source