opus-5.5
Public AI IQ model profile with source-backed benchmark results and derived ranking context.
IQ
137
EQ
n/a
Effective Cost
$20.57
IQ Rank
#3
opus-5.5 API pricing — full price table, workload cost examples, and cheaper alternatives.
IQ Dimensions
| Dimension | IQ | Coverage |
|---|---|---|
| Abstract Reasoning | 131 | 2/3 |
| Mathematical Reasoning | 140 | 1/5 |
| Academic Reasoning | 145 | 4/6 |
| Programmatic Reasoning | 147 | 2/6 |
| Computer Use | 141 | 0/6 |
| Reliability | 121 | 2/7 |
Benchmark Results
| Benchmark | Score | Dimension |
|---|---|---|
| AA Long Context Reasoning v1.1 | 84.6667 | Reliability |
| AA Omniscience | 46.4167 | Reliability |
| ARC-AGI-1 | 98.5 | Abstract Reasoning |
| ARC-AGI-2 | 93.3333 | Abstract Reasoning |
| CritPt | 31.7143 | Academic Reasoning |
| Humanity's Last Exam | 61.3531 | Academic Reasoning |
| MMMU-Pro | 87.6879 | Academic Reasoning |
| ProgramBench | 65 | Programmatic Reasoning |
| ProofBench 1.1 | 100 | Mathematical Reasoning |
| SciCode | 66.8981 | Academic Reasoning |
| Terminal-Bench 4.0 | 59.596 | Programmatic Reasoning |
Compare
Frequently Asked Questions
- What is the IQ of opus-5.5?
- opus-5.5 has an estimated IQ of 137, which ranks #3 out of 143 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- How much does opus-5.5 cost?
- opus-5.5 costs $4.00 per million input tokens and $20.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $20.57 per million input-plus-output tokens.
- Is opus-5.5 open source?
- No — opus-5.5 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- When was opus-5.5 released?
- opus-5.5 was publicly released on September 22, 2026.
- How large is the context window of opus-5.5?
- opus-5.5 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.