What it measures
- Coding
- Reasoning
- Research
- Multimodal
- Agentic
Five-axis capability index
Equal-weight average of five normalized capability indices: coding, reasoning, research, multimodal and agentic.
How to read the score
0–100 index; higher is better.
Sourced Ranking
| Rank | Model | Provider | Score | Source | Source Type | Verified |
|---|
Limitations
- Relative to the selected cohort and benchmarks
- Equal weights do not represent every use case
- Missing axes produce no overall score
- Calculated by gpt.college from normalized benchmark scores; not the raw AA Intelligence Index.
- Each axis = benchmark score / current cohort leader × 100. Overall = the arithmetic mean of all five axes, rounded to one decimal. Requires all five scores.
unknown
gpt.college overall methodology
Calculated by gpt.college from normalized benchmark scores; not the raw AA Intelligence Index. Each axis = benchmark score / current cohort leader × 100. Overall = the arithmetic mean of all five axes, rounded to one decimal. Requires all five scores.