AutomationBench-AA - Sales - Raw Objective Completion: leaderboard
Metric: Raw Objective Completion (%). Source: artificialanalysis.ai. 167 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.6 (xHigh) | 87.62 |
| 2 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 86.9 |
| 3 | Grok 4.5 (High) | 86.55 |
| 4 | GPT-6 (Max) | 85.91 |
| 5 | Grok 4.6 (Medium) | 85.91 |
| 6 | Grok 4.6 (High) | 85.28 |
| 7 | GPT-6 (High) | 84.61 |
| 8 | GPT-6 (xHigh) | 84.44 |
| 9 | GPT-6 (Medium) | 84.3 |
| 10 | GLM-5.3 Flash | 84.27 |
| 11 | Qwen3.8-Flash-Next | 84.09 |
| 12 | Qwen 3.8 Max (0902) | 83.43 |
| 13 | Grok 4.6 (Low) | 82.36 |
| 14 | GPT-5.6 Sol (Max) | 81.93 |
| 15 | GLM-5.3 (Max) | 81.78 |
Interactive version: theaggregate.ai/benchmark?slug=automationbench-aa-sales-raw-objective-completion · How It Works · Data refreshed daily, snapshot 2026-09-19.