DeepSeek V3 · 发布历史
DeepSeek DeepSeek V3 系列已收录 7 次发布和 92 个测试版本。
DeepSeek V3 命名系列,按官方发布名称分别记录版本。
全部版本
- DeepSeek-V3.221 项测试
- DeepSeek-V3.2-Speciale14 项测试
- DeepSeek-V3.2-Exp17 项测试
- DeepSeek-V3.1-Terminus12 项测试
- DeepSeek-V3.113 项测试
- DeepSeek-V3-03244 项测试
- DeepSeek-V334 项测试
已收录测试 · 92
- MMLU-Pro · DeepSeek-V3.2 report Table 2; MMLU-Pro (EM); unit not printedDeepSeek-V3.2
- GPQA Diamond · DeepSeek-V3.2 report Table 2; GPQA Diamond (Pass@1); unit not printedDeepSeek-V3.2
- HLE · DeepSeek-V3.2 report Table 2; HLE (Pass@1); reasoning/no-tools table row; unit not printedDeepSeek-V3.2
- LiveCodeBench · DeepSeek-V3.2 report Table 2; LiveCodeBench (Pass@1-COT); unit not printedDeepSeek-V3.2
- Codeforces · DeepSeek-V3.2 report Table 2; Codeforces (Rating); unit printed as ratingDeepSeek-V3.2
- AIME · DeepSeek-V3.2 report Table 2; 2025 (Pass@1); unit not printedDeepSeek-V3.2
- HMMT · DeepSeek-V3.2 report Table 2; February 2025 (Pass@1); unit not printedDeepSeek-V3.2
- HMMT · DeepSeek-V3.2 report Table 2; November 2025 (Pass@1); unit not printedDeepSeek-V3.2
- IMOAnswerBench · DeepSeek-V3.2 report Table 2; IMOAnswerBench (Pass@1); unit not printedDeepSeek-V3.2
- Terminal Bench 2.0 · DeepSeek-V3.2 report Table 2; Terminal Bench 2.0 (Acc); unit not printedDeepSeek-V3.2
- SWE Verified · DeepSeek-V3.2 report Table 2; SWE Verified (Resolved); unit not printedDeepSeek-V3.2
- SWE Multilingual · DeepSeek-V3.2 report Table 2; SWE Multilingual (Resolved); unit not printedDeepSeek-V3.2
- BrowseComp · DeepSeek-V3.2 report Table 2; BrowseComp (Pass@1); without context management; unit not printedDeepSeek-V3.2
- BrowseComp · DeepSeek-V3.2 report Table 2; BrowseComp (Pass@1); context-management result marked *; unit not printedDeepSeek-V3.2
- BrowseCompZh · DeepSeek-V3.2 report Table 2; BrowseCompZh (Pass@1); unit not printedDeepSeek-V3.2
- HLE · DeepSeek-V3.2 report Table 2; HLE (Pass@1); Search Agent table section; unit not printedDeepSeek-V3.2
- tau2-Bench · DeepSeek-V3.2 report Table 2; tau2-Bench (Pass@1); category average; unit not printedDeepSeek-V3.2
- MCP-Universe · DeepSeek-V3.2 report Table 2; MCP-Universe (SuccessRate); unit not printedDeepSeek-V3.2
- MCP-Mark · DeepSeek-V3.2 report Table 2; MCP-Mark (Pass@1); unit not printedDeepSeek-V3.2
- Tool-Decathlon · DeepSeek-V3.2 report Table 2; Tool-Decathlon (Pass@1); unit not printedDeepSeek-V3.2
- HLE · Official HLE template; V3.2 thinking; unit not printedDeepSeek-V3.2
- IMO · 2025 competition; categorical medal resultDeepSeek-V3.2-Speciale
- IOI · 2025 competition; categorical medal resultDeepSeek-V3.2-Speciale
- AIME · DeepSeek-V3.2 report Table 3; Speciale explicitly named; 2025 (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- HMMT · DeepSeek-V3.2 report Table 3; Speciale explicitly named; February 2025 (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- HMMT · DeepSeek-V3.2 report Table 3; Speciale explicitly named; November 2025 (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- IMOAnswerBench · DeepSeek-V3.2 report Table 3; Speciale explicitly named; IMOAnswerBench (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- LiveCodeBench · DeepSeek-V3.2 report Table 3; Speciale explicitly named; LiveCodeBench (Pass@1-COT); unit not printedDeepSeek-V3.2-Speciale
- Codeforces · DeepSeek-V3.2 report Table 3; Speciale explicitly named; Codeforces (Rating); unit printed as ratingDeepSeek-V3.2-Speciale
- GPQA Diamond · DeepSeek-V3.2 report Table 3; Speciale explicitly named; GPQA Diamond (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- HLE · DeepSeek-V3.2 report Table 3; Speciale explicitly named; HLE (Pass@1); unit not printedDeepSeek-V3.2-Speciale
- IMO · 2025; overall points and gold medal; DeepSeek-V3.2 report Table 4DeepSeek-V3.2-Speciale
- CMO · 2025; overall points and gold medal; DeepSeek-V3.2 report Table 4DeepSeek-V3.2-Speciale
- IOI · 2025; overall points and gold medal; DeepSeek-V3.2 report Table 4DeepSeek-V3.2-Speciale
- ICPC WF · 2025; overall submissions/solved count and gold medal; DeepSeek-V3.2 report Table 4DeepSeek-V3.2-Speciale
- MMLU-Pro · DeepSeek card version unspecified; Exact MatchDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1、DeepSeek-V3
- GPQA Diamond · Diamond subset; task snapshot unspecifiedDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1、DeepSeek-V3
- Humanity's Last Exam · Text-only subset as stated in V3.1 and later comparison cards; task revision unspecifiedDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1
- LiveCodeBench · Version unspecified; Pass@1DeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus
- AIME · 2025 edition; Pass@1DeepSeek-V3.2-Exp、DeepSeek-V3.1
- HMMT · 2025 edition; reported score, metric not stated in V3.2-Exp cardDeepSeek-V3.2-Exp
- Codeforces · Rating; contest snapshot unspecifiedDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus
- Aider-Polyglot · Version unspecified; AccuracyDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3
- BrowseComp · Version unspecified; AccuracyDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1
- BrowseComp-zh · Version unspecified; AccuracyDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1
- SimpleQA · Internal search agent protocol; task version unspecifiedDeepSeek-V3.2-Exp、DeepSeek-V3.1-Terminus、DeepSeek-V3.1
- SWE Verified · V3.2-Exp comparison; agent/task version unspecifiedDeepSeek-V3.2-Exp
- SWE-bench Multilingual · V3.2-Exp comparison; agent/task version unspecifiedDeepSeek-V3.2-Exp
- Terminal-Bench · Task version unspecified in V3.1-Terminus/Exp cardDeepSeek-V3.2-Exp
- General synthesized agentic tasks · 50-task ablation; Pass@1; unit printed as %DeepSeek-V3.2-Exp
- General synthesized agentic tasks · 50-task ablation; Pass@2; unit printed as %DeepSeek-V3.2-Exp
- General synthesized agentic tasks · 50-task ablation; Pass@4; unit printed as %DeepSeek-V3.2-Exp
- SWE-bench Verified · Agent mode; task snapshot unspecifiedDeepSeek-V3.1-Terminus、DeepSeek-V3.1、DeepSeek-V3
- SWE-bench Multilingual · Agent mode; task snapshot unspecifiedDeepSeek-V3.1-Terminus、DeepSeek-V3.1
- Terminal-Bench · Terminus 1 framework; task version unspecifiedDeepSeek-V3.1-Terminus、DeepSeek-V3.1
- LiveCodeBench · 2408-2505; Pass@1DeepSeek-V3.1
- Codeforces-Div1 · Div1; contest snapshot unspecifiedDeepSeek-V3.1
- HMMT · 2025 competition; Pass@1DeepSeek-V3.1
- MMLU-Pro · V3-0324 overview does not state metric or set versionDeepSeek-V3-0324
- GPQA · V3-0324 overview does not state variant or metricDeepSeek-V3-0324
- AIME · Year/metric not stated in V3-0324 overviewDeepSeek-V3-0324
- LiveCodeBench · Version/metric not stated in V3-0324 overviewDeepSeek-V3-0324
- LiveCodeBench · Version unspecified; Pass@1-CoTDeepSeek-V3
- Codeforces · Percentile; contest snapshot unspecifiedDeepSeek-V3
- AIME · 2024 edition; Pass@1DeepSeek-V3
- MMLU · DeepSeek-V3 Technical Report Table 6; MMLU (EM); unit not printedDeepSeek-V3
- MMLU-Redux · DeepSeek-V3 Technical Report Table 6; MMLU-Redux (EM); unit not printedDeepSeek-V3
- DROP · DeepSeek-V3 Technical Report Table 6; DROP (3-shot F1); unit not printedDeepSeek-V3
- IF-Eval · DeepSeek-V3 Technical Report Table 6; IF-Eval (PromptStrict); unit not printedDeepSeek-V3
- SimpleQA · DeepSeek-V3 Technical Report Table 6; SimpleQA (Correct); unit not printedDeepSeek-V3
- FRAMES · DeepSeek-V3 Technical Report Table 6; FRAMES (Acc.); unit not printedDeepSeek-V3
- LongBench v2 · DeepSeek-V3 Technical Report Table 6; LongBench v2 (Acc.); unit not printedDeepSeek-V3
- HumanEval-Mul · DeepSeek-V3 Technical Report Table 6; HumanEval-Mul (Pass@1); unit not printedDeepSeek-V3
- LiveCodeBench · DeepSeek-V3 Technical Report Table 6; LiveCodeBench (Pass@1); unit not printedDeepSeek-V3
- Aider-Edit · DeepSeek-V3 Technical Report Table 6; Aider-Edit (Acc.); unit not printedDeepSeek-V3
- MATH-500 · DeepSeek-V3 Technical Report Table 6; MATH-500 (EM); unit not printedDeepSeek-V3
- CNMO · DeepSeek-V3 Technical Report Table 6; CNMO 2024 (Pass@1); unit not printedDeepSeek-V3
- CLUEWSC · DeepSeek-V3 Technical Report Table 6; CLUEWSC (EM); unit not printedDeepSeek-V3
- C-Eval · DeepSeek-V3 Technical Report Table 6; C-Eval (EM); unit not printedDeepSeek-V3
- C-SimpleQA · DeepSeek-V3 Technical Report Table 6; C-SimpleQA (Correct); unit not printedDeepSeek-V3
- Arena-Hard · DeepSeek-V3 Technical Report Table 7; Arena-Hard; unit not printedDeepSeek-V3
- AlpacaEval 2.0 · DeepSeek-V3 Technical Report Table 7; AlpacaEval 2.0 (length-controlled win rate); unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Chat; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Chat-Hard; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Safety; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Reasoning; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Average; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Chat; maj@6; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Chat-Hard; maj@6; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Safety; maj@6; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Reasoning; maj@6; unit not printedDeepSeek-V3
- RewardBench · DeepSeek-V3 Technical Report Table 8; Average; maj@6; unit not printedDeepSeek-V3