DeepSeek V4 Pro
DeepSeek
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date |
|---|---|---|
|
SWE-bench Verified
coding_agent
|
91.97%
|
11.06.2026 |
|
SWE-bench Pro
coding_agent
|
69.25%
|
11.06.2026 |
|
Terminal Bench 2.1
coding_agent
|
65.63%
|
11.06.2026 |
|
NL2Repo-Bench
coding_agent
|
29.08%
|
11.06.2026 |
|
VIBE-V2
coding_agent
|
60.93%
|
11.06.2026 |
|
SVG-Bench
coding_agent
|
85.09%
|
11.06.2026 |
|
BrowseComp
general_agent
|
91.15%
|
11.06.2026 |
|
GDPVal
general_agent
|
77.44%
|
11.06.2026 |
|
SpreadSheetBench-v1
general_agent
|
91.76%
|
11.06.2026 |
|
YC-Bench
general_agent
|
22.73%
|
11.06.2026 |
|
MCP-Atlas
general_agent
|
83.45%
|
11.06.2026 |
|
SWE-bench Multilingual
coding_agent
|
85.56%
|
28.08.2026 |
|
SWE Atlas - QnA
coding_agent
|
80.66%
|
28.08.2026 |
|
SWE Atlas - TW
coding_agent
|
64.07%
|
28.08.2026 |
|
SWE Atlas - RF
coding_agent
|
79.53%
|
28.08.2026 |
|
SWE-Marathon
coding_agent
|
36.73%
|
28.08.2026 |
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
98.67%
|
28.08.2026 |
|
NL2Repo
coding_agent
|
78.77%
|
28.08.2026 |
|
Cybergym
general_agent
|
90.28%
|
28.08.2026 |
|
ProgramBench
coding_agent
|
18.14%
|
28.08.2026 |
|
PostTrainBench
coding_agent
|
38.91%
|
28.08.2026 |
|
Harbor-Index
coding_agent
|
51.57%
|
28.08.2026 |
|
Hy-Backend 2.0 (Internal)
coding_agent
|
32.48%
|
28.08.2026 |
|
Hy-CompanyBench V2 (Internal)
general_agent
|
80.65%
|
28.08.2026 |
|
WideSearch
general_agent
|
91.19%
|
28.08.2026 |
|
$OneMillion-Bench
general_capabilities
|
76.81%
|
28.08.2026 |
|
DRACO
general_agent
|
51.71%
|
28.08.2026 |
|
Hy-LifeSearch (Internal)
general_agent
|
32.65%
|
28.08.2026 |
|
Hy-BrowseComp-Pro2 (Internal)
general_agent
|
46.50
|
28.08.2026 |
|
OfficeQA Pro
general_agent
|
96.93%
|
28.08.2026 |
|
Toolathlon Verified
general_agent
|
92.42%
|
28.08.2026 |
|
Apex-Agents
general_agent
|
74.03%
|
28.08.2026 |
|
SkillsBench Avg5
coding_agent
|
97.27%
|
28.08.2026 |
|
JobBench
general_agent
|
69.91%
|
28.08.2026 |
|
WorkSpaceBench
general_agent
|
42.86%
|
28.08.2026 |
|
Agents' Last Exam
general_agent
|
53.30%
|
28.08.2026 |
|
GDPVal-AA v2
general_agent
|
86.29%
|
28.08.2026 |
|
Automation-Bench
general_agent
|
44.55%
|
28.08.2026 |
|
BankerToolBench
general_agent
|
51.11%
|
28.08.2026 |
|
E-Bench (Internal)
general_agent
|
39.88%
|
28.08.2026 |
|
E-Bench-Code (Internal)
coding_agent
|
64.30
|
28.08.2026 |
|
Hy-FinAgentBench (Internal)
domain_finance
|
66.67%
|
28.08.2026 |
|
Hy-FinmodelBench v2 (Internal)
domain_finance
|
60.70%
|
28.08.2026 |
|
BioMysteryBench
stem_reasoning
|
36.81%
|
28.08.2026 |
|
HLE (with tools)
stem_reasoning
|
90.47%
|
28.08.2026 |
|
CritPt (no tools)
stem_reasoning
|
54.89%
|
28.08.2026 |
|
GPQA Diamond
stem_reasoning
|
97.16%
|
28.08.2026 |
|
Humanity's Last Exam
stem_reasoning
|
76.89%
|
28.08.2026 |
|
SUPERChem
stem_reasoning
|
39.00%
|
28.08.2026 |
|
ArXivMath
stem_reasoning
|
37.41%
|
28.08.2026 |
|
HorizonMath (pass@4)
stem_reasoning
|
12.92%
|
28.08.2026 |
|
MathArena Apex 2025
stem_reasoning
|
52.37%
|
28.08.2026 |
|
BrokenArXiv
stem_reasoning
|
32.16%
|
28.08.2026 |
|
Claw-Eval Avg
coding_agent
|
69.89%
|
11.06.2026 |
|
DeepSWE
coding_agent
|
86.24%
|
28.08.2026 |
|
Hy-SWE Max Verified (Internal)
coding_agent
|
79.15%
|
28.08.2026 |