DeepSeek-R1 · SWE-bench Verified(Agent mode; task snapshot unspecified) 49.2% · 主文证据(ev-r1-010)

DeepSeek-R1 的 SWE-bench Verified · Agent mode; task snapshot unspecified 官方出处。DeepSeek-R1 reported reasoning configuration · 49.2%。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 “| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |”。证据 ev-r1-010。

原文与定位

DeepSeek-R1 · SWE-bench Verified(Agent mode; task snapshot unspecified),DeepSeek-R1 reported reasoning configuration配置,Resolved 49.2%(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 “| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |”。 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 | | | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
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 “| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |”
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 · SWE-bench Verified(Agent mode; task snapshot unspecified),DeepSeek-R1 reported reasoning configuration配置,Resolved 49.2%(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 “| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |”,https://huggingface.co/deepseek-ai/DeepSeek-R1。Benchlog https://benchlog.lekshome.cc/evidence/r1/ev-r1-010/

关联成绩与条件

DeepSeek-R1 · SWE-bench Verified 成绩与配置
指标与成绩配置与评测条件证据关系
Resolved49.2%原文 49.2 · 单位 %
公布 未确认
DeepSeek-R1 reported reasoning configuration
设置
Maximum generation length 32,768 tokens. For sampled benchmarks: temperature=0.6, top_p=0.95, 64 responses per query to estimate Pass@1.
未知项
Per-benchmark sampling use is not itemized beyond the card preface.
工具
工具条件未记录
推理预算
输出上限 32768 tokens
框架
未记录
协议
未说明
条件
Source R1 evaluation table; max generation length and sampling preface retained in configuration.

直接支持该成绩

在排名中查看此成绩