Claude Opus 5
Anthropic
Parameters
—
Architecture
—
Released
—
License
—
Openness Index Score
25.0/100
About
Proprietary Anthropic frontier model; included as comparison model in the Tencent Hy4 preview benchmark appendix.
Benchmark Scores
| Benchmark | Score | Date |
|---|---|---|
|
SWE-bench Pro
coding_agent
|
99.00%
|
28.08.2026 |
|
DeepSWE
coding_agent
|
94.64%
|
28.08.2026 |
|
SWE Atlas - QnA
coding_agent
|
88.14%
|
28.08.2026 |
|
SWE Atlas - TW
coding_agent
|
100.00%
|
28.08.2026 |
|
SWE Atlas - RF
coding_agent
|
100.00%
|
28.08.2026 |
|
SWE-Marathon
coding_agent
|
100.00%
|
28.08.2026 |
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
96.90%
|
28.08.2026 |
|
NL2Repo
coding_agent
|
100.00%
|
28.08.2026 |
|
ProgramBench
coding_agent
|
52.98%
|
28.08.2026 |
|
PostTrainBench
coding_agent
|
74.74%
|
28.08.2026 |
|
Harbor-Index
coding_agent
|
100.00%
|
28.08.2026 |
|
Hy-Backend 2.0 (Internal)
coding_agent
|
60.26%
|
28.08.2026 |
|
Hy-SWE Max Verified (Internal)
coding_agent
|
100.00%
|
28.08.2026 |
|
Hy-CompanyBench V2 (Internal)
general_agent
|
100.00%
|
28.08.2026 |
|
WideSearch
general_agent
|
95.50%
|
28.08.2026 |
|
$OneMillion-Bench
general_capabilities
|
100.00%
|
28.08.2026 |
|
Hy-LifeSearch (Internal)
general_agent
|
70.20%
|
28.08.2026 |
|
Hy-BrowseComp-Pro2 (Internal)
general_agent
|
100.00%
|
28.08.2026 |
|
OfficeQA Pro
general_agent
|
100.00%
|
28.08.2026 |
|
MCP-Atlas
general_agent
|
100.00%
|
28.08.2026 |
|
Toolathlon Verified
general_agent
|
97.21%
|
28.08.2026 |
|
Apex-Agents
general_agent
|
100.00%
|
28.08.2026 |
|
SkillsBench Avg5
coding_agent
|
95.18%
|
28.08.2026 |
|
JobBench
general_agent
|
100.00%
|
28.08.2026 |
|
WorkSpaceBench
general_agent
|
100.00%
|
28.08.2026 |
|
GDPVal-AA v2
general_agent
|
100.00%
|
28.08.2026 |
|
Automation-Bench
general_agent
|
86.14%
|
28.08.2026 |
|
BankerToolBench
general_agent
|
100.00%
|
28.08.2026 |
|
E-Bench (Internal)
general_agent
|
91.28%
|
28.08.2026 |
|
E-Bench-Code (Internal)
coding_agent
|
96.84%
|
28.08.2026 |
|
Hy-FinAgentBench (Internal)
domain_finance
|
92.59%
|
28.08.2026 |
|
Hy-FinmodelBench v2 (Internal)
domain_finance
|
100.00%
|
28.08.2026 |
|
BioMysteryBench
stem_reasoning
|
94.51%
|
28.08.2026 |
|
HLE (with tools)
stem_reasoning
|
92.37%
|
28.08.2026 |
|
CritPt (no tools)
stem_reasoning
|
89.91%
|
28.08.2026 |
|
GPQA Diamond
stem_reasoning
|
98.87%
|
28.08.2026 |
|
Humanity's Last Exam
stem_reasoning
|
100.00%
|
28.08.2026 |
|
SUPERChem
stem_reasoning
|
100.00%
|
28.08.2026 |
|
ArXivMath
stem_reasoning
|
71.22%
|
28.08.2026 |
|
HorizonMath (pass@4)
stem_reasoning
|
25.28%
|
28.08.2026 |
|
MathArena Apex 2025
stem_reasoning
|
100.00%
|
28.08.2026 |
|
BrokenArXiv
stem_reasoning
|
100.00%
|
28.08.2026 |
|
DRACO
general_agent
|
100.00%
|
28.08.2026 |
|
SWE-bench Multilingual
coding_agent
|
100.00%
|
28.08.2026 |
|
Agents' Last Exam
general_agent
|
68.40%
|
28.08.2026 |