AutomataBench — leaderboard
Metric: Weighted pass@1 (%). Source: www.automatabench.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 45.28 |
| 2 | Claude Opus 4.8 | 30.22 |
| 3 | DeepSeek V4 Pro | 28.34 |
| 4 | Gemini 3.1 Pro (Preview) | 14.7 |
| 5 | Grok 4.3 | 6.51 |
Interactive version: theaggregate.ai/benchmark?slug=automatabench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.