AutoLab: leaderboard
AutoLab evaluates AI agents on iterative performance-engineering tasks across model development, puzzle/challenge tasks, and system optimization.
Metric: Overall Score (imported). Source: autolab.moe. Source: benchmarklist.com. Saturation forecast: Around August 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 68 | #63 |
| 2 | Gemini 3.1 Pro (Preview) | 50 | #58 |
| 3 | Kimi K2.6 | 46 | #104 |
| 4 | MiMo-V2.5-Pro | 45 | #158 |
| 5 | GLM-5 | 43 | #141 |
| 6 | DeepSeek V4 Pro | 38 | #102 |
| 7 | GPT-5.4 | 36 | #79 |
| 8 | Grok 4.20 | 35 | #175 |
| 9 | Qwen 3.6 Plus | 27 | #120 |
| 10 | MiniMax-M2.7 | 27 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=autolab · How It Works · Data refreshed daily, snapshot 2026-10-20.