Opus-4.6
Anthropic
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
HLE (with tools)
stem_reasoning
|
69.88%
|
26.06.2026 |
#21/49
better than 58%
|
|
MMLU-Pro
knowledge
|
93.87%
|
26.06.2026 |
#3/48
better than 96%
|
|
GPQA Diamond
stem_reasoning
|
94.33%
|
26.06.2026 |
#17/80
better than 76%
|
|
Humanity's Last Exam
stem_reasoning
|
71.78%
|
26.06.2026 |
#19/71
better than 71%
|
|
LiveCodeBench v6
stem_reasoning
|
93.59%
|
26.06.2026 |
#12/49
better than 71%
|
|
HMMT Feb 26
stem_reasoning
|
98.06%
|
26.06.2026 |
#5/44
better than 88%
|
|
IMOAnswerBench
stem_reasoning
|
74.86%
|
26.06.2026 |
#19/30
better than 34%
|
|
Apex-Agents
general_agent
|
45.02%
|
26.06.2026 |
#11/24
better than 57%
|
|
Terminal-Bench 2.0
coding_agent
|
91.53%
|
26.06.2026 |
#4/23
better than 77%
|
|
SWE-bench Verified
coding_agent
|
92.20%
|
26.06.2026 |
#5/60
better than 92%
|
|
SWE-bench Pro
coding_agent
|
63.88%
|
26.06.2026 |
#29/77
better than 63%
|
|
SWE-bench Multilingual
coding_agent
|
85.80%
|
26.06.2026 |
#8/48
better than 81%
|
|
GDPVal-AA v2
general_agent
|
88.42%
|
26.06.2026 |
#11/38
better than 73%
|
|
MCP-Atlas
general_agent
|
79.90%
|
26.06.2026 |
#21/54
better than 62%
|
|
Toolathlon Verified
general_agent
|
38.72%
|
26.06.2026 |
#28/35
better than 18%
|
|
BrowseComp
general_agent
|
90.56%
|
26.06.2026 |
#6/45
better than 86%
|
|
Apex-Shortlist (no tools)
stem_reasoning
|
92.99%
|
26.06.2026 |
#3/11
better than 80%
|
What is a good HLE (with tools) score? What is a good MMLU-Pro score? What is a good GPQA Diamond score?
No comments yet
Be the first to share your thoughts!