Anthropic
opus-4.8
Public AI IQ model profile with source-backed benchmark results and derived ranking context. Proprietary
IQ
130
EQ
122
Effective Cost
$43.65
IQ Rank
#2
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| mathematical reasoning | 135 | 2/5 |
| scientific reasoning | 140 | 4/4 |
| abstract reasoning | 101 | 3/3 |
| app building | 141 | 3/4 |
| production engineering | 139 | 6/7 |
| computer use | 135 | 7/7 |
| reliability | 120 | 3/3 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA Omniscience | 27 | reliability |
| Agents' Last Exam | 15.8 | computer-use |
| ARC-AGI-1 | 92 | abstract-reasoning |
| ARC-AGI-2 | 72.1 | abstract-reasoning |
| ARC-AGI-3 | 1.5 | abstract-reasoning |
| Arena.ai Overall | 1483 | |
| AttuneBench Composite | 54.6 | |
| BrowseComp | 84.3 | computer-use |
| BullshitBench v2 | 94 | reliability |
| CritPt | 20.9 | scientific-reasoning |
| DeepSWE | 58.19 | production-engineering |
| DesignArena Full Stack | 1337 | app-building |