Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| GPQA Diamond | 93.6 | 94.6 |
| Humanity's Last Exam | 57.9 | — |
coding
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| SWE-bench Verified | 88.6 | — |
| SWE-Bench Pro | 69.2 | 64.6 |
agent
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| BrowseComp | 84.3 | 90.4 |
| Toolathlon | 59.9 | 58 |
| MCP Atlas | 82.2 | — |
multimodal
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| CharXiv Reasoning | 89.9 | — |
| ScreenSpot Pro | 87.9 | — |
| MMMU-Pro | — | 83 |
math
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| FrontierMath | — | 89 |
general
| Benchmark | Claude Opus 4.8 | GPT-5.6 Sol |
|---|---|---|
| MRCR v2 | — | 91.5 |
Category Winners
coding
89.4
math
98.2
reasoning
91.4
general
93.3
multimodal
89.2
agent
78.3