Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Opus 4.6 | GPT-5.1 High |
|---|---|---|
| GPQA Diamond | 91.3 | 88.1 |
| Humanity's Last Exam | 53.1 | — |
| ARC-AGI v2 | 68.8 | — |
math
| Benchmark | Claude Opus 4.6 | GPT-5.1 High |
|---|---|---|
| AIME 2025 | 99.8 | 99.6 |
coding
| Benchmark | Claude Opus 4.6 | GPT-5.1 High |
|---|---|---|
| SWE-bench Verified | 80.8 | — |
multimodal
| Benchmark | Claude Opus 4.6 | GPT-5.1 High |
|---|---|---|
| MMMU-Pro | 77.3 | — |
| CharXiv Reasoning | 77.4 | — |
agent
| Benchmark | Claude Opus 4.6 | GPT-5.1 High |
|---|---|---|
| OSWorld | 72.7 | — |
| BrowseComp | 84 | — |
| MCP Atlas | 62.7 | — |
Category Winners
coding
82.4
math
83.8
reasoning
86.7
general
85.3
multimodal
68.3
agent
66.0