Automation-BenchBrowse 296

Automation-Bench

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

Version not specifiedExact reported variant
Agents11 ranked models17 reported values4 reportsHigher is better

Top rankings

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

11
RankModelBest scoreBest reported setting
1DeepSeek V4.1 FlashDeepSeek54.8%Reported configurationDeepSeek report1 value · 1 reportSep 10, 2026 · source
2Kimi K3Moonshot AI30.8%max effortMoonshot AI report1 value · 1 reportJul 17, 2026 · source
3GPT-5.6 SolOpenAI29.7%max effortMoonshot AI report2 values · 2 reportsJul 17, 2026 · source
4Claude Fable 5Anthropic29.1%max effortMoonshot AI report2 values · 2 reportsJul 17, 2026 · source
5Claude Opus 4.8Anthropic27.2%max effortMoonshot AI report3 values · 3 reportsJul 17, 2026 · source
6GPT-5.5OpenAI22.7%xhigh effortMoonshot AI report3 values · 3 reportsJul 17, 2026 · source
7GPT-5.6 TerraOpenAI15.2%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
8GPT-5.6 LunaOpenAI14.9%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
9Gemini 3.5 FlashGoogle14.5%Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source
10GLM-5.2Z.ai12.9%max effortMoonshot AI report1 value · 1 reportJul 17, 2026 · source
11Gemini 3.1 Pro PreviewGoogle9.6%Reported configurationAnthropic report1 value · 1 reportJun 9, 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.

DeepSeek's official V4.1-Flash release table; exact source label Automation-Bench retained; benchmark-maintainer contexts remain separate.

Method / source