Thinking mode; temperature=1.0 and 128K context as stated in Section 4.1. Tool-use benchmarks use the standard function-call format; math tasks use the paper's boxed-answer prompt.
未知项
Row-specific tool harness, context-management and scaffold details are retained in each result condition.、The main table does not print percent signs.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Official DeepSeek-V3.2 report Table 2; thinking-mode main evaluation. Temperature=1.0 and 128K context; row-specific tool and prompt protocols retained.
条件
DeepSeek-V3.2 column; table does not print a percent sign unless noted. BrowseComp values are separated by context-management protocol.
DeepSeek-V3.2 · SWE Multilingual · DeepSeek-V3.2 report Table 2; SWE Multilingual (Resolved); unit not printed · Scores and configurations
DeepSeek-V3.2 record for SWE Multilingual · DeepSeek-V3.2 report Table 2; SWE Multilingual (Resolved); unit not printed. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
DeepSeek-V3.2 · SWE Multilingual scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Resolved70.2Reported 70.2 · Unit not specified
Published Unconfirmed
DeepSeek-V3.2 thinking
Settings
Thinking mode; temperature=1.0 and 128K context as stated in Section 4.1. Tool-use benchmarks use the standard function-call format; math tasks use the paper's boxed-answer prompt.
Unknowns
Row-specific tool harness, context-management and scaffold details are retained in each result condition.、The main table does not print percent signs.
Tools
Tool access not recorded
Reasoning budget
not recorded
Framework
not recorded
Protocol
Official DeepSeek-V3.2 report Table 2; thinking-mode main evaluation. Temperature=1.0 and 128K context; row-specific tool and prompt protocols retained.
Conditions
DeepSeek-V3.2 column; table does not print a percent sign unless noted. BrowseComp values are separated by context-management protocol.