GPT-5.2-Codex vs GLM 5.1
Côte à côte. Chaque métrique. Chaque benchmark.
| Type | GPT-5.2-Codex | GLM 5.1 |
|---|---|---|
| Provider |  OpenAI |  z-ai |
| score moyen | 70.6 | 70.2 |
| Prix d'entrée | $1.75 | $0.95 |
| Prix de sortie | $14.00 | $3.15 |
| Fenêtre de contexte | 400K tokens (~200 books) | 203K tokens (~101 books) |
| Sorti le | 2026-01-14 | 2026-04-07 |
| Code source ouvert | Proprietary | Open Source |
Scores de benchmark
8 benchmarks · GPT-5.2-Codex: 6, GLM 5.1: 2
| Benchmark | Catégorie | 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 |