Neura Intelligence Index
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 85.7 | 90.4 |
| Humanity's Last Exam | 42.8 | 28.8 |
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| AIME 2025 | 95.7 | — |
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 73.8 | 78.8 |
| TerminalBench | 33.3 | — |
| SWE-Bench Pro | — | 56.6 |
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| BrowseComp | 52 | — |
| Toolathlon | — | 39.8 |
| MCP Atlas | — | 74.1 |
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| MMMU | — | 86 |
| MMMU-Pro | — | 78.8 |
| CharXiv Reasoning | — | 81.5 |
| ScreenSpot Pro | — | 68.2 |
| Benchmark | GLM-4.7 | Qwen3.6 Plus |
|---|---|---|
| MMMLU | — | 89.5 |