DeepSeek-V4-Pro (Preview) · SWE-bench Pro(Pro; Resolved) 52.1% · 主文证据(ev-v4-pro-preview-021)
DeepSeek-V4-Pro (Preview) 的 SWE-bench Pro · Pro; Resolved 官方出处。DeepSeek-V4-Pro (Preview) Non-Think · 52.1%。见《DeepSeek-V4-Pro official Hugging Face model card》Official model card / table headed “| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |” / complete row containing “| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | **55.4** |”。证据 ev-v4-pro-preview-021。
原文与定位
DeepSeek-V4-Pro (Preview) · SWE-bench Pro(Pro; Resolved),DeepSeek-V4-Pro (Preview) Non-Think配置,Resolved 52.1%(具体成绩公布时间未确认)。见《DeepSeek-V4-Pro official Hugging Face model card》Official model card / table headed “| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |” / complete row containing “| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | **55.4** |”。 查看成绩条件
| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max | | SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | **55.4** |
- 官方材料
- DeepSeek-V4-Pro official Hugging Face model card
- 定位
- 主文 · Official model card / table headed “| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |” / complete row containing “| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | **55.4** |”
- 材料版本
- HF revision b5968e9190ef611bbf34a7229255be88a0e937c1; 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 (Preview) · SWE-bench Pro(Pro; Resolved),DeepSeek-V4-Pro (Preview) Non-Think配置,Resolved 52.1%(具体成绩公布时间未确认)。官方出处 DeepSeek-V4-Pro official Hugging Face model card(主文,HF revision b5968e9190ef611bbf34a7229255be88a0e937c1; current card snapshot)Official model card / table headed “| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |” / complete row containing “| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | **55.4** |”,https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro。Benchlog https://benchlog.lekshome.cc/evidence/v4-pro-preview/ev-v4-pro-preview-021/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Resolved52.1%原文 52.1 · 单位 % 公布 未确认 | DeepSeek-V4-Pro (Preview) Non-Think
| 直接支持该成绩 在排名中查看此成绩 |