DeepSeek-R1 · MMLU-Pro(DeepSeek card version unspecified; Exact Match) 84% · 主文证据(ev-r1-003)
DeepSeek-R1 的 MMLU-Pro · DeepSeek card version unspecified; Exact Match 官方出处。DeepSeek-R1 reported reasoning configuration · 84%。见《DeepSeek-R1 official Hugging Face model card》Official model card / table headed “| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |” / complete row containing “| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |”。证据 ev-r1-003。
原文与定位
DeepSeek-R1 · MMLU-Pro(DeepSeek card version unspecified; Exact Match),DeepSeek-R1 reported reasoning configuration配置,Exact Match 84%(具体成绩公布时间未确认)。见《DeepSeek-R1 official Hugging Face model card》Official model card / table headed “| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |” / complete row containing “| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |”。 查看成绩条件
| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 | | | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
- 官方材料
- DeepSeek-R1 official Hugging Face model card
- 定位
- 主文 · Official model card / table headed “| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |” / complete row containing “| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |”
- 材料版本
- HF revision 56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad; 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-R1 · MMLU-Pro(DeepSeek card version unspecified; Exact Match),DeepSeek-R1 reported reasoning configuration配置,Exact Match 84%(具体成绩公布时间未确认)。官方出处 DeepSeek-R1 official Hugging Face model card(主文,HF revision 56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad; current card snapshot)Official model card / table headed “| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |” / complete row containing “| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |”,https://huggingface.co/deepseek-ai/DeepSeek-R1。Benchlog https://benchlog.lekshome.cc/evidence/r1/ev-r1-003/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Exact Match84%原文 84 · 单位 % 公布 未确认 | DeepSeek-R1 reported reasoning configuration
| 直接支持该成绩 在排名中查看此成绩 |