AutoLab — leaderboard

AutoLab evaluates AI agents on iterative performance-engineering tasks across model development, puzzle/challenge tasks, and system optimization.

Metric: Overall Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 11 models tracked.

Top models

#ModelScore
1Claude Opus 4.668
2Gemini 3.1 Pro (Preview)50
3MiMo-V2.5-Pro45
4GLM-543
5DeepSeek V4 Pro38
6GPT-5.436
7Grok 4.2035
8Qwen 3.6 Plus27
9MiniMax-M2.727

Interactive version: theaggregate.ai/benchmark?slug=autolab · How the rankings work · Data refreshed daily, snapshot 2026-07-22.