Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | ChatGPT-4o Latest | Claude Opus 4.6 |
|---|---|---|
| GPQA Diamond | 84 | 91.3 |
| Humanity's Last Exam | — | 53.1 |
| ARC-AGI v2 | — | 68.8 |
math
| Benchmark | ChatGPT-4o Latest | Claude Opus 4.6 |
|---|---|---|
| AIME 2025 | — | 99.8 |
coding
| Benchmark | ChatGPT-4o Latest | Claude Opus 4.6 |
|---|---|---|
| SWE-bench Verified | — | 80.8 |
multimodal
| Benchmark | ChatGPT-4o Latest | Claude Opus 4.6 |
|---|---|---|
| MMMU-Pro | — | 77.3 |
| CharXiv Reasoning | — | 77.4 |
agent
| Benchmark | ChatGPT-4o Latest | Claude Opus 4.6 |
|---|---|---|
| OSWorld | — | 72.7 |
| BrowseComp | — | 84 |
| MCP Atlas | — | 62.7 |
Category Winners
coding
82.4
math
83.8
reasoning
87.0
general
84.8
multimodal
69.1
agent
66.2