DeepSeek-V4-Pro-0813 · AutomationBench(Public set; metric/version details not stated in V4-0813/0731 cards) 31.8 · 主文证据(ev-v4-pro-0813-006)
DeepSeek-V4-Pro-0813 的 AutomationBench · Public set; metric/version details not stated in V4-0813/0731 cards 官方出处。DeepSeek-V4-Pro-0813, max reasoning effort · 31.8。见《DeepSeek-V4-Pro-0813 official Hugging Face model card》Official model card / table headed “| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |” / complete row containing “| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |”。证据 ev-v4-pro-0813-006。
原文与定位
DeepSeek-V4-Pro-0813 · AutomationBench(Public set; metric/version details not stated in V4-0813/0731 cards),DeepSeek-V4-Pro-0813, max reasoning effort配置,Reported score 31.8(具体成绩公布时间未确认)。见《DeepSeek-V4-Pro-0813 official Hugging Face model card》Official model card / table headed “| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |” / complete row containing “| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |”。 查看成绩条件
| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) | | AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |
- 官方材料
- DeepSeek-V4-Pro-0813 official Hugging Face model card
- 定位
- 主文 · Official model card / table headed “| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |” / complete row containing “| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |”
- 材料版本
- HF revision 72e1d3230f6c080a530b0a1d46f8eb4602340597; current card snapshot
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
DeepSeek-V4-Pro-0813 · AutomationBench(Public set; metric/version details not stated in V4-0813/0731 cards),DeepSeek-V4-Pro-0813, max reasoning effort配置,Reported score 31.8(具体成绩公布时间未确认)。官方出处 DeepSeek-V4-Pro-0813 official Hugging Face model card(主文,HF revision 72e1d3230f6c080a530b0a1d46f8eb4602340597; current card snapshot)Official model card / table headed “| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |” / complete row containing “| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |”,https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813。Benchlog https://benchlog.lekshome.cc/evidence/deepseek-v4-pro-0813/ev-v4-pro-0813-006/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Reported score31.8原文 31.8 · 单位 未标注 公布 未确认 | DeepSeek-V4-Pro-0813, max reasoning effort
| 直接支持该成绩 在排名中查看此成绩 |