AutomationBench-AA - Support - Raw Objective Completion: leaderboard
Metric: Raw Objective Completion (%). Source: artificialanalysis.ai. 167 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (xHigh) | 92.43 |
| 2 | GPT-6 (Max) | 91.93 |
| 3 | GPT-6 (High) | 91.34 |
| 4 | Grok 4.6 (High) | 89.71 |
| 5 | GPT-5.6 Sol (Max) | 89.55 |
| 6 | Qwen 3.8 Max (0902) | 89.46 |
| 7 | Grok 4.6 (xHigh) | 89.41 |
| 8 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 89.28 |
| 9 | GPT-5.6 Sol (xHigh) | 88.71 |
| 10 | Grok 4.6 (Medium) | 88.61 |
| 11 | GLM-5.3 Flash | 88.36 |
| 12 | GLM-5.3 (Max) | 88.16 |
| 13 | Grok 4.5 (High) | 87.65 |
| 14 | GPT-6 (Medium) | 87.49 |
| 15 | Qwen3.8-Flash-Next | 87.29 |
Interactive version: theaggregate.ai/benchmark?slug=automationbench-aa-support-raw-objective-completion · How It Works · Data refreshed daily, snapshot 2026-09-19.