Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 3.1 Pro | GLM-5 |
|---|---|---|
| GPQA Diamond | 94.3 | — |
| Humanity's Last Exam | 51.4 | — |
| ARC-AGI v2 | 77.1 | — |
coding
| Benchmark | Gemini 3.1 Pro | GLM-5 |
|---|---|---|
| SWE-bench Verified | 80.6 | 77.8 |
| SWE-Bench Pro | 54.2 | — |
| SciCode | 59 | — |
multimodal
| Benchmark | Gemini 3.1 Pro | GLM-5 |
|---|---|---|
| MMMU-Pro | 80.5 | — |
agent
| Benchmark | Gemini 3.1 Pro | GLM-5 |
|---|---|---|
| BrowseComp | 85.9 | 75.9 |
| MCP Atlas | 69.2 | 67.8 |
| APEX Agents | 33.5 | — |
Category Winners
coding
Z
GLM-577.3
reasoning
89.6
general
53.5
multimodal
82.2
agent
69.1