GPT-5.2-Codex scores 26.4 on the Respan Index (#74), ahead of GLM-4.7 at 25.9 (#76). GLM-4.7 leads on 1 of the 1 benchmarks both report. GLM-4.7 is 4.8x cheaper per token at list price. GPT-5.2-Codex has the larger context window (400K tokens).
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works