Programmierung: API-Fehler
Programmierung
API-Fehler
Sieh, welche KI-Modelle bei Programmierung am ehesten auf API-Fehler stoßen, damit du Schwachstellen schneller erkennst.
Fehlergründe
39/39
Modelle filtern
Keine Modelle entsprechen der aktuellen Suche und den Filtern.
| Rang | Modell | Unternehmen | API-Fehler-Anzahl | Kategorie-Score | Gesamtkosten | Korrekte Tests | Antwortzeit (Durchschnitt) |
|---|---|---|---|---|---|---|---|
| #281 | Nemotron 3 Super medium | NVIDIA | 3 | 0.3 | $0.081 | 0/3 | 147.3s |
| #325 | Gemini 3 PRO Preview medium | 3 | 0.3 | $0.385 | 0/3 | 0ms | |
| #382 | Command A+ medium | Cohere | 3 | 0.3 | $0.064 | 0/3 | 93.1s |
| #387 | Command A+ high | Cohere | 3 | 0.3 | $0.079 | 0/3 | 92.7s |
| #390 | Command A+ none | Cohere | 3 | 0.3 | $0.000 | 0/3 | 80.8s |
| #391 | Command A+ low | Cohere | 3 | 0.3 | $0.073 | 0/3 | 86.4s |
| #192 | Ember-1 max | Fireworks | 2 | 0.5 | $3.264 | 1/3 | 105.1s |
| #235 | Trinity Large Thinking low | Arcee AI | 2 | 0.5 | $0.918 | 1/3 | 344.4s |
| #268 | Ring 2.6 1t medium | Inclusionai | 2 | 0.5 | $0.102 | 1/3 | 59.6s |
| #296 | Hy3 preview medium | Tencent | 2 | 0.5 | $0.049 | 1/3 | 31.4s |
| #326 | Ling 2.6 1t default | Inclusionai | 2 | 0.4 | $0.016 | 0/3 | 10.6s |
| #331 | Hy3 preview high | Tencent | 2 | 0.5 | $0.135 | 1/3 | 99.8s |
| #348 | Ling 2.6 Flash default | Inclusionai | 2 | 0.5 | $0.002 | 1/3 | 11.2s |
| #349 | Hy3 preview low | Tencent | 2 | 0.5 | $0.042 | 1/3 | 27.9s |
| #350 | Ring 2.6 1t default | Inclusionai | 2 | 0.5 | $0.026 | 1/3 | 143.8s |