LLM Stats (AutomationBench): leaderboard

Metric: Score (%). Source: llm-stats.com. 18 models tracked.

Top models

#ModelScore
1Muse Spark 1.349.4
2GLM-5.3 Flash48.8
3GLM-5.348.2
4GPT-641.4
5Hy4 preview32.1
6DeepSeek V4 Pro (0813)31.8
7Claude Fable 5.131.4
8Kimi K330.8
9Gemini 3.7 Flash30.4
10Qwen 3.8 Max27.3
11Claude Opus 526
12DeepSeek-V4-Flash-Vision-Exp25.7
13DeepSeek V4 Flash (0731)25.1
14GPT-5.6 Sol18.1
15Claude Fable 517.4

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-automationbench · How It Works · Data refreshed daily, snapshot 2026-09-05.