← Benchmarks
Beste KI-Modelle im Programmierung-Benchmark
Ranking von KI-Modellen nach Programmierung-Benchmark-Score.
| Rang | Modell | Anbieter | Punktzahl | Datensatz | Version | Datum |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 4 | Anthropic | 93 | internal-demo | v1 | 2026-07-01 |
| 2 | GPT-4.1 | OpenAI | 92 | internal-demo | v1 | 2026-07-01 |
| 3 | Claude Sonnet 4 | Anthropic | 90 | internal-demo | v1 | 2026-07-01 |
| 4 | Gemini 2.5 Pro | 90 | internal-demo | v1 | 2026-07-01 | |
| 5 | o3 | OpenAI | 89 | internal-demo | v1 | 2026-07-01 |
| 6 | GPT-4o | OpenAI | 88 | internal-demo | v1 | 2026-07-01 |
| 7 | DeepSeek Chat | DeepSeek | 87 | internal-demo | v1 | 2026-07-01 |
| 8 | DeepSeek Reasoner | DeepSeek | 85 | internal-demo | v1 | 2026-07-01 |
| 9 | Gemini 2.5 Flash | 84 | internal-demo | v1 | 2026-07-01 |