GLM-5.3 scores 49.4 on the Respan Index (#24), ahead of GPT-5.4 Pro at 49.1 (#25). GPT-5.4 Pro leads on 5 of the 6 benchmarks both report. GLM-5.3 is 31x cheaper per token at list price. GPT-5.4 Pro has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 46.3% |
| WeirdML (Håvard Tveit Ihle) | 75.4% | 57.4% |
Higher is better. Each score links to where it was published.