Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | DeepSeek-V3 0324 | Gemini 3.5 Flash |
|---|---|---|
| GPQA Diamond | 68.4 | — |
| Humanity's Last Exam | — | 40.2 |
| ARC-AGI v2 | — | 72.1 |
coding
| Benchmark | DeepSeek-V3 0324 | Gemini 3.5 Flash |
|---|---|---|
| SWE-Bench Pro | — | 55.1 |
multimodal
| Benchmark | DeepSeek-V3 0324 | Gemini 3.5 Flash |
|---|---|---|
| MMMU-Pro | — | 83.6 |
| CharXiv Reasoning | — | 84.2 |
agent
| Benchmark | DeepSeek-V3 0324 | Gemini 3.5 Flash |
|---|---|---|
| Toolathlon | — | 56.5 |
| MCP Atlas | — | 83.6 |
general
| Benchmark | DeepSeek-V3 0324 | Gemini 3.5 Flash |
|---|---|---|
| MRCR v2 | — | 26.6 |
Category Winners
coding
32.7
reasoning
78.0
general
24.3
multimodal
83.0
agent
82.0