Benchmarks · agentic
AutomationBench-AA
AutomationBench-AA: building workflow automations; partial-credit score.
104 models · 189 results · data as of 2026-11-06 · artificialanalysis.ai ↗
Leaderboard
Gemini 4 Carbon high
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 27 more models under All models in settings.
More from this benchmark
87 published measuresScore vs any published measure87 measures: sub-scores, splits, counts
81 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | |||||
|---|---|---|---|---|---|
| Gemini 4 Carbon high | 0.553 | 0.939 | 203.0 | 0.309 | 22,822 |
| Gemini 4 Argon high | 0.531 | 0.935 | 205.0 | 0.312 | 22,822 |
| Kimi K3.1 max | 0.46 | 0.918 | 232.0 | 0.353 | 22,822 |
| Sonnet 5.5 max | 0.455 | 0.91 | 220.0 | 0.344 | 21,553 |
| Opus 5.5 max | 0.412 | 0.904 | 276.0 | 0.42 | 22,822 |
| DeepSeek V4.1 Flash max | 0.355 | 0.846 | 252.0 | 0.384 | 22,822 |
| DeepSeek V4.1 Flash 1017 high | 0.358 | 0.895 | 314.0 | 0.479 | 22,797 |
| GPT-6 Astra max | 0.416 | 0.888 | 292.0 | 0.444 | 22,822 |
| Muse Wonder (Max) | 0.391 | 0.876 | 303.0 | 0.461 | 22,822 |
| Grok 4.6 xhigh | 0.346 | 0.883 | 333.0 | 0.507 | 22,822 |
| GPT-6.1 Sol xhigh | 0.371 | 0.883 | 330.0 | 0.502 | 22,822 |
| Hy4 | 0.362 | 0.909 | 408.0 | 0.621 | 22,822 |
| Grok 4.7 xhigh | 0.377 | 0.877 | 420.0 | 0.639 | 22,822 |
| MiMo V2.6 Flash | 0.315 | 0.887 | 370.0 | 0.563 | 22,822 |
| GLM 5.3 max | 0.294 | 0.872 | 363.0 | 0.553 | 22,822 |
| Gemini 3.7 Flash high | 0.3 | 0.837 | 364.0 | 0.554 | 22,822 |
| Ling 3.1 Flash | 0.236 | 0.876 | 395.0 | 0.613 | 22,253 |
| GPT-6 Sol xhigh | 0.326 | 0.881 | 460.0 | 0.7 | 22,822 |
| Gemini 3.8 Flash medium | 0.311 | 0.779 | 237.0 | 0.361 | 22,738 |
| GLM 5.3 Flash max | 0.254 | 0.864 | 417.0 | 0.635 | 22,822 |
| GPT-6.1 Terra max | 0.33 | 0.859 | 396.0 | 0.603 | 22,822 |
| GPT-5.6 Sol max | 0.303 | 0.866 | 466.0 | 0.709 | 22,822 |
| GPT-5.6 Terra max | 0.245 | 0.837 | 449.0 | 0.683 | 22,822 |
| Fable 5.1 max | 0.321 | 0.881 | 467.0 | 0.713 | 22,744 |
| MiMo V2.6 Pro | 0.254 | 0.876 | 483.0 | 0.739 | 22,686 |
All results
189 rows| # | Model | Effort | AutomationBench-AA | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 77.8% | $0.67 | $1.89 |
| 2 | Gemini 4 Carbon | medium | 77.6% | $0.59 | $1.65 |
| 3 | Gemini 4 Argon | high | 77.5% | $0.87 | $1.22 |
| 4 | Kimi K3.1 | max | 73.3% | $0.83 | $0.83 |
| 5 | Sonnet 5.5 | max | 71.8% | $0.016 | $1.03 |
| 6 | Opus 5.5 | max | 69.5% | $0.022 | $1.43 |
| 7 | DeepSeek V4.1 Flash | max | 68.9% | ||
| 8 | DeepSeek V4.1 Flash 1017 | high | 68.5% | free | $0.14 |
| 9 | GPT-6 Astra | max | 68.5% | $0.068 | $1.60 |
| 10 | Muse Wonder (Max) | max | 68.1% | $0.48 | $0.72 |
| 11 | GPT-6 Astra | xhigh | 67.2% | $0.060 | $1.41 |
| 12 | Grok 4.6 | xhigh | 67.0% | $0.067 | $0.66 |
| 13 | Grok 4.6 | high | 66.7% | ||
| 14 | DeepSeek V4.1 Flash 1017 | max | 66.6% | free | $0.17 |
| 15 | GPT-6 Astra | high | 66.6% | $0.055 | $1.30 |
| 16 | GPT-6.1 Sol | xhigh | 66.6% | $0.015 | $0.25 |
| 17 | Hy4 | 65.6% | $0.073 | $0.25 | |
| 18 | Grok 4.7 | xhigh | 65.6% | $0.089 | $0.95 |
| 19 | Sonnet 5.5 | xhigh | 65.5% | $0.006 | $0.42 |
| 20 | Opus 5.5 | xhigh | 65.0% | $0.013 | $0.88 |
| 21 | GPT-6.1 Sol | max | 64.9% | $0.017 | $0.30 |
| 22 | GPT-6 Astra | medium | 64.6% | $0.050 | $1.18 |
| 23 | GPT-6.1 Sol | high | 64.5% | $0.013 | $0.23 |
| 24 | MiMo V2.6 Flash | 64.1% | free | $0.017 | |
| 25 | Grok 4.7 | high | 63.5% | $0.079 | $0.85 |
| 26 | Gemini 4 Carbon | low | 63.5% | $0.32 | $0.90 |
| 27 | Opus 5.5 | high | 63.2% | $0.011 | $0.70 |
| 28 | Grok 4.6 | medium | 63.2% | ||
| 29 | GPT-6.1 Sol | medium | 62.6% | $0.011 | $0.20 |
| 30 | GLM 5.3 | max | 62.2% | $0.048 | $0.46 |