AI BENCHY Kategoriefehler
Anti-KI-Tricks: API-Fehler
Anti-KI-Tricks
API-Fehler
Sieh, welche KI-Modelle bei Anti-KI-Tricks am ehesten auf API-Fehler stoßen, damit du Schwachstellen schneller erkennst. Sortieren nach: Korrekte Tests ↓.
Fehlergründe
| Rang | Modell | Unternehmen | API-Fehler-Anzahl | Kategorie-Score | Korrekte Tests | Antwortzeit (Durchschnitt) |
|---|---|---|---|---|---|---|
| #72 | DeepSeek V3.2 medium | DeepSeek | 1 | 8.2 | 3/4 | 24.2s |
| #89 | Hy3 preview low | Tencent | 1 | 8.3 | 3/4 | 9.32s |
| #93 | Qwen3.6 Plus Preview medium | Qwen | 1 | 8.3 | 3/4 | 11.7s |
| #82 | Hy3 preview high | Tencent | 2 | 6.4 | 2/4 | 15.1s |
| #92 | Laguna M.1 medium | Poolside | 1 | 6.5 | 2/4 | 4.87s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 1 | 6.4 | 2/4 | 16.5s |
| #107 | Laguna Xs.2 medium | Poolside | 1 | 6.9 | 2/4 | 2.68s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 6.4 | 2/4 | 1.20s |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 1 | 4.8 | 1/4 | 584ms |
| #133 | DeepSeek V3.2 none | DeepSeek | 1 | 3.2 | 0/4 | 9.35s |
| #145 | Laguna M.1 none | Poolside | 1 | 3.4 | 0/4 | 705ms |
| #146 | Laguna Xs.2 none | Poolside | 1 | 3.0 | 0/4 | 534ms |