GLM-5 scores 25.5 on the Respan Index (#78), ahead of Grok 4 at 25.4 (#79). GLM-5 leads on 4 of the 7 benchmarks both report. Grok 4 has the larger context window (256K tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 1411 |
| AIME 2025 | 96.7% | 91.7% |
| SimpleBench (SimpleBench) | 53.2% | 60.5% |
Higher is better. Each score links to where it was published.