Agentic benchmark
AutomationBench leaderboard
Every model the catalog carries a published AutomationBench value for, ranked by that value.
CategoryAgentic
MeasureAgent task-completion score
Tasks600 public automation tasks
DifficultyLong-horizon automation
Published byKimi K3: Open Frontier Intelligence
An agent benchmark for completing automation workflows in reproducible task environments.
AutomationBench ranking
14 models with a published AutomationBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Agent task-completion score |
|---|---|---|---|
| 1 |  DeepSeek V4.1 Flash | DeepSeek | 54.8 |
| 2 |  Atria Dawn Preview | Shanghai Artificial Intelligence Laboratory | 53.8 |
| 3 |  Muse Spark 1.3 | Meta | 49.4 |
| 4 |  GLM-5.3-Flash | Z.AI | 48.8 |
| 5 | GLM-5.3 | Z.AI | 48.2 |
| 6 |  GPT-6 Astra | OpenAI | 41.4 |
| 7 |  Hy4 preview | Tencent | 32.1 |
| 8 | DeepSeek V4 Pro 0813 | DeepSeek | 31.8 |
| 9 |  Claude Fable 5.1 | Anthropic | 31.4 |
| 10 |  Kimi K3 | Moonshot AI | 30.8 |
| 11 |  Gemini 3.7 Flash | 30.4 | |
| 12 |  Qwen3.8 Max | Alibaba | 27.3 |
| 13 | Claude Opus 5 | Anthropic | 26.0 |
| 14 | DeepSeek V4 Flash 0731 | DeepSeek | 25.1 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.