DeepSeek-R1-0528 · Humanity's Last Exam(R1-0528 card: text-only prompts; task revision unspecified) 17.7% · 主文证据(ev-r1-0528-006)
DeepSeek-R1-0528 的 Humanity's Last Exam · R1-0528 card: text-only prompts; task revision unspecified 官方出处。DeepSeek-R1-0528 reported reasoning configuration · 17.7%。见《DeepSeek-R1-0528 official Hugging Face model card》Official model card / table headed “| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528” / complete row containing “| | Humanity's Last Exam (Pass@1) | 8.5 | 17.7”。证据 ev-r1-0528-006。
原文与定位
DeepSeek-R1-0528 · Humanity's Last Exam(R1-0528 card: text-only prompts; task revision unspecified),DeepSeek-R1-0528 reported reasoning configuration配置,Pass@1 17.7%(具体成绩公布时间未确认)。见《DeepSeek-R1-0528 official Hugging Face model card》Official model card / table headed “| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528” / complete row containing “| | Humanity's Last Exam (Pass@1) | 8.5 | 17.7”。 查看成绩条件
| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528 | | Humanity's Last Exam (Pass@1) | 8.5 | 17.7 Note: We use Agentless framework to evaluate model performance on SWE-Verified. We only evaluate text-only prompts in HLE testsets. GPT-4.1 is employed to act user role in Tau-bench evaluation.
- 官方材料
- DeepSeek-R1-0528 official Hugging Face model card
- 定位
- 主文 · Official model card / table headed “| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528” / complete row containing “| | Humanity's Last Exam (Pass@1) | 8.5 | 17.7”
- 材料版本
- HF revision 4236a6af538feda4548eca9ab308586007567f52; current card snapshot; read in full
- 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-R1-0528 · Humanity's Last Exam(R1-0528 card: text-only prompts; task revision unspecified),DeepSeek-R1-0528 reported reasoning configuration配置,Pass@1 17.7%(具体成绩公布时间未确认)。官方出处 DeepSeek-R1-0528 official Hugging Face model card(主文,HF revision 4236a6af538feda4548eca9ab308586007567f52; current card snapshot; read in full)Official model card / table headed “| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528” / complete row containing “| | Humanity's Last Exam (Pass@1) | 8.5 | 17.7”,https://huggingface.co/deepseek-ai/DeepSeek-R1-0528。Benchlog https://benchlog.lekshome.cc/evidence/r1-0528/ev-r1-0528-006/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Pass@117.7%原文 17.7 · 单位 % 公布 未确认 | DeepSeek-R1-0528 reported reasoning configuration
| 直接支持该成绩 在排名中查看此成绩 |