Anthropic
opus-4.6
Public AI IQ model profile with source-backed benchmark results and derived ranking context. Proprietary
IQ
122
EQ
118
Effective Cost
$40.45
IQ Rank
#7
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| mathematical reasoning | 131 | 5/5 |
| scientific reasoning | 137 | 4/4 |
| abstract reasoning | 101 | 3/3 |
| app building | 133 | 4/4 |
| production engineering | 118 | 5/7 |
| computer use | 126 | 4/7 |
| reliability | 113 | 3/3 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA Omniscience | 11 | reliability |
| Agents' Last Exam | 14.1 | computer-use |
| AIME | 95.625 | mathematical-reasoning |
| ARC-AGI-1 | 94 | abstract-reasoning |
| ARC-AGI-2 | 69.2 | abstract-reasoning |
| ARC-AGI-3 | 0.5 | abstract-reasoning |
| Arena.ai Overall | 1504 | |
| AttuneBench Composite | 54.3 | |
| BrowseComp | 84 | computer-use |
| BullshitBench v2 | 87 | reliability |
| CritPt | 12.6 | scientific-reasoning |
| DeepSWE | 27.6 | production-engineering |