GLM 5.1 vs GPT-5.2-Codex
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | GLM 5.1 | GPT-5.2-Codex |
|---|---|---|
| Provider |  z-ai |  OpenAI |
| puntuación promedio | 70.2 | 70.6 |
| Precio de entrada | $0.95 | $1.75 |
| Precio de salida | $3.15 | $14.00 |
| Ventana de contexto | 203K tokens (~101 books) | 400K tokens (~200 books) |
| Publicado el | 2026-04-07 | 2026-01-14 |
| Código abierto | Open Source | Proprietary |
Puntuaciones de benchmark
8 benchmarks · GLM 5.1: 2, GPT-5.2-Codex: 6
| Benchmark | Categoría | GLM 5.1 | GPT-5.2-Codex |
|---|---|---|---|
| LiveBench — Agentic Coding | coding | 55.0 | 51.7 |
| LiveBench — Coding | coding | 75.4 | 83.6 |
| LiveBench — Data Analysis | reasoning | 63.2 | 78.2 |
| LiveBench — If | language | 68.5 | 66.5 |
| LiveBench — Language | language | 71.8 | 73.7 |
| LiveBench — Mathematics | math | 84.9 | 88.8 |
| LiveBench — Overall | knowledge | 70.2 | 74.3 |
| LiveBench — Reasoning | reasoning | 72.5 | 77.7 |