Anthropic
opus-4.7
Public AI IQ model profile with source-backed benchmark results and derived ranking context. Proprietary
IQ
127
EQ
120
Effective Cost
$55.82
IQ Rank
#4
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| mathematical reasoning | 132 | 5/5 |
| scientific reasoning | 138 | 4/4 |
| abstract reasoning | 102 | 3/3 |
| app building | 142 | 4/4 |
| production engineering | 131 | 6/7 |
| computer use | 131 | 6/7 |
| reliability | 115 | 3/3 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA Omniscience | 26 | reliability |
| Agents' Last Exam | 18.4 | computer-use |
| AIME | 96.25 | mathematical-reasoning |
| ARC-AGI-1 | 92 | abstract-reasoning |
| ARC-AGI-2 | 75.8 | abstract-reasoning |
| ARC-AGI-3 | 0.2 | abstract-reasoning |
| Arena.ai Overall | 1502 | |
| AttuneBench Composite | 53.6 | |
| BrowseComp | 79.3 | computer-use |
| BullshitBench v2 | 74 | reliability |
| CritPt | 12 | scientific-reasoning |
| DeepSWE | 54.2 | production-engineering |