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