AutomationBench 1.0.6
Created by Zapier, 31 Jul 2026 · Higher is better · Website
- Other labs
- Reported in a later post or card
Results
| Model | Score | Source |
|---|---|---|
| MiniMax M3.1 Flash19 Oct 2026 · MiniMax | 62.8% | MiniMax M3.1 Flash: Redefining Agent Performance and CostChecked A person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.AutomationBench v1.0.6Source image |
| Hy44 Nov 2026 · Tencent | 56.2% | Introducing Hy4Checked A person checked this number against its source on 5 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.AutomationBench v1.0.6; official method; highest reasoning settingSource image |
| DeepSeek-V4.1-Flash10 Sep 2026 · DeepSeek | 54.8% | DeepSeek-V4.1-Flash: Smarter, Faster, More EfficientCorroborated The same number is printed in 2 other lab documents: 1 2v1.0.6; set named in the technical report the post links, which prints the same figureSource image |
| LongCat-2.51 Nov 2026 · Meituan | 51.8% | LongCat-2.5: Native Multimodality for Agentic TasksChecked A person checked this number against its source on 2 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.v1.0.6; official evaluation codeOur capture |
| Hy4 preview28 Aug 2026 · Tencent | 36.3% | Introducing Hy4Checked A person checked this number against its source on 8 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.re-evaluated at Hy4 launch; AutomationBench v1.0.6; official method; reported laterSource image |
