Anti-KI-Tricks: Falsche Antwort
Anti-KI-Tricks
Falsche Antwort
Sieh, welche KI-Modelle bei Anti-KI-Tricks am ehesten auf Falsche Antwort stoßen, damit du Schwachstellen schneller erkennst.
Fehlergründe
258/258
Modelle filtern
Keine Modelle entsprechen der aktuellen Suche und den Filtern.
| Rang | Modell | Unternehmen | Falsche Antwort-Anzahl | Kategorie-Score | Gesamtkosten | Korrekte Tests | Antwortzeit (Durchschnitt) |
|---|---|---|---|---|---|---|---|
| #390 | Cobuddy medium | Baidu | 1 | 0.9 | $0.000 | 3/4 | 10.00s |
| #395 | gpt-oss-120b none | OpenAI | 1 | 0.7 | $0.016 | 2/4 | 32.8s |
| #399 | Qwen3.5-9B medium | Qwen | 1 | 0.5 | $0.106 | 1/4 | 34.4s |
| #400 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 0.7 | $5.599 | 2/4 | 3.46s |
| #402 | Grok 4.1 Fast medium | X AI | 1 | 0.9 | $0.069 | 3/4 | 3.81s |
| #403 | Laguna M.1 medium | Poolside | 1 | 0.7 | $0.033 | 2/4 | 4.87s |
| #408 | Ling 3.0 Tiny high | Inclusionai | 1 | 0.6 | $0.000 | 2/4 | 24.9s |
| #409 | Ling 3.0 Tiny low | Inclusionai | 1 | 0.7 | $0.000 | 2/4 | 25.3s |
| #410 | Ling 3.0 Tiny medium | Inclusionai | 1 | 0.7 | $0.000 | 2/4 | 23.7s |
| #413 | Elephant Alpha default | Openrouter | 1 | 0.7 | $0.000 | 2/4 | 963ms |
| #418 | Laguna Xs.2 medium | Poolside | 1 | 0.7 | $0.015 | 2/4 | 2.68s |
| #419 | Hy3 preview none | Tencent | 1 | 0.5 | $0.007 | 1/4 | 11.1s |
| #422 | Grok Build 0.1 none | X AI | 1 | 0.9 | $0.547 | 3/4 | 6.30s |
| #428 | Span-02 default | Respan | 1 | 0.6 | $0.001 | 2/3 | 2.38s |
| #429 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 0.6 | $0.000 | 2/4 | 1.20s |