Kimi K2.5 scores 27.1 on the Respan Index (#73), ahead of GPT-5.2-Codex at 26.4 (#74). They split the 2 benchmarks both report evenly. 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