Claude Opus 4.6 vs GPT-5.3-Codex
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Claude Opus 4.6 | GPT-5.3-Codex |
|---|---|---|
| Provider |  Anthropic |  OpenAI |
| puntuación promedio | 57.5 | 52.2 |
| Precio de entrada | $5.00 | $1.75 |
| Precio de salida | $25.00 | $14.00 |
| Ventana de contexto | 1.0M tokens (~500 books) | 400K tokens (~200 books) |
| Publicado el | 2026-02-04 | 2026-02-24 |
| Código abierto | Proprietary | Proprietary |
Puntuaciones de benchmark
5 benchmarks · Claude Opus 4.6: 2, GPT-5.3-Codex: 2
| Benchmark | Categoría | Claude Opus 4.6 | GPT-5.3-Codex |
|---|---|---|---|
| APEX-Agents | agentic | 31.7 | 31.7 |
| PostTrainBench | knowledge | 23.2 | 17.8 |
| SWE-Bench verified | coding | 78.7 | 74.8 |
| Terminal Bench | coding | 74.7 | 77.3 |
| WeirdML | coding | 77.9 | 79.3 |