Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | MAI-Code-1-Flash | o1-mini |
|---|---|---|
| GPQA Diamond | 84.6 | 60 |
| Humanity's Last Exam | 18 | — |
coding
| Benchmark | MAI-Code-1-Flash | o1-mini |
|---|---|---|
| SWE-bench Verified | 71.6 | — |
| SWE-Bench Pro | 51.2 | — |
math
| Benchmark | MAI-Code-1-Flash | o1-mini |
|---|---|---|
| FrontierMath | 6.3 | — |
Category Winners
coding
40.1
math
13.6
reasoning
52.9