Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
coding
| Benchmark | Devstral Small 1.1 | GPT-4o |
|---|---|---|
| SWE-bench Verified | 53.6 | — |
reasoning
| Benchmark | Devstral Small 1.1 | GPT-4o |
|---|---|---|
| GPQA Diamond | — | 53.6 |
Category Winners
coding
22.5
reasoning
23.3
| Benchmark | Devstral Small 1.1 | GPT-4o |
|---|---|---|
| SWE-bench Verified | 53.6 | — |
| Benchmark | Devstral Small 1.1 | GPT-4o |
|---|---|---|
| GPQA Diamond | — | 53.6 |