benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
AutomationBench-AA leaderboard
AutomationBench-AA
7 models tested · Updated 2026-07-21 · Verified sources only
Kimi K3
leads at
52.7%
1
Kimi K3
Moonshot ·
Artificial Analysis
· 2026-07-21
#1 on AutomationBench-AA. Simulated SaaS workflow tasks.
52.7%
2
Grok 4.5
xAI ·
Artificial Analysis
· 2026-07-21
#2 on AutomationBench-AA.
51.4%
3
GPT-5.6 Sol
OpenAI ·
Artificial Analysis
· 2026-07-21
#3 on AutomationBench-AA.
51.2%
4
Gemini 3.6 Flash
Google ·
Artificial Analysis
· 2026-07-21
#4 on AutomationBench-AA. Tied with GPT-5.6 Sol.
51.1%
5
Claude Fable 5
Anthropic ·
Artificial Analysis
· 2026-07-21
#5 on AutomationBench-AA.
48.6%
6
Claude Opus 4.8
Anthropic ·
Artificial Analysis
· 2026-07-21
#6 on AutomationBench-AA.
48.5%
7
GLM-5.2
Z AI ·
Artificial Analysis
· 2026-07-21
AA independent eval on simulated SaaS workflows. Partial score metric.
27.8%