Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Mythos Preview | DeepSeek-V4-Pro-0813 |
|---|---|---|
| GPQA Diamond | 94.6 | — |
| Humanity's Last Exam | 64.7 | 60 |
coding
| Benchmark | Claude Mythos Preview | DeepSeek-V4-Pro-0813 |
|---|---|---|
| SWE-bench Verified | 93.9 | — |
| SWE-Bench Pro | 77.8 | — |
general
| Benchmark | Claude Mythos Preview | DeepSeek-V4-Pro-0813 |
|---|---|---|
| MMMLU | 92.7 | — |
agent
| Benchmark | Claude Mythos Preview | DeepSeek-V4-Pro-0813 |
|---|---|---|
| BrowseComp | 86.9 | — |
| Toolathlon | — | 74.1 |
multimodal
| Benchmark | Claude Mythos Preview | DeepSeek-V4-Pro-0813 |
|---|---|---|
| CharXiv Reasoning | 93.2 | — |
Category Winners
coding
97.8
reasoning
94.3
general
83.3
multimodal
91.3
agent
96.9