Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | ChatGPT-4o Latest | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | 84 | — |
| Humanity's Last Exam | — | 57.2 |
agent
| Benchmark | ChatGPT-4o Latest | GPT-5.5 Pro |
|---|---|---|
| BrowseComp | — | 90.1 |
math
| Benchmark | ChatGPT-4o Latest | GPT-5.5 Pro |
|---|---|---|
| FrontierMath | — | 39.6 |
Category Winners
math
57.5
reasoning
93.4
agent
89.6