Neura Intelligence Index
| Benchmark | GLM-5.1 | Qwen3 Max Thinking |
|---|---|---|
| GPQA Diamond | 86.2 | 87.4 |
| Humanity's Last Exam | 52.3 | — |
| Benchmark | GLM-5.1 | Qwen3 Max Thinking |
|---|---|---|
| SWE-Bench Pro | 58.4 | — |
| SWE-bench Verified | — | 75.3 |
| Benchmark | GLM-5.1 | Qwen3 Max Thinking |
|---|---|---|
| BrowseComp | 79.3 | 53.9 |
| Toolathlon | 40.7 | 18.8 |
| MCP Atlas | 71.8 | — |
| Benchmark | GLM-5.1 | Qwen3 Max Thinking |
|---|---|---|
| MMMLU | — | 84.4 |