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) |
|---|---|---|---|---|---|---|---|
| #289 | gpt-oss-120b medium | OpenAI | 1 | 0.7 | $0.030 | 2/4 | 10.2s |
| #292 | Claude Sonnet 5 none | Anthropic | 1 | 0.5 | $1.095 | 1/4 | 3.60s |
| #306 | Dots 3 Note Preview medium | Dots Studio | 1 | 0.9 | $0.000 | 3/4 | 7.76s |
| #311 | Step 5 Preview low | Stepfun | 1 | 0.7 | $4.110 | 2/4 | 9.50s |
| #320 | Gemma 4 26B A4B none | 1 | 0.8 | $0.031 | 3/4 | 1.28s | |
| #321 | GLM 5V Turbo medium | Z.ai | 1 | 0.7 | $0.457 | 2/4 | 10.8s |
| #323 | Claude Opus 4.7 none | Anthropic | 1 | 0.8 | $0.505 | 3/4 | 2.12s |
| #332 | Granite 4.2 8B low | IBM Granite | 1 | 0.8 | $0.036 | 3/4 | 11.7s |
| #340 | KAT Coder AIR V2.5 high | Kwaipilot | 1 | 0.7 | $0.077 | 2/4 | 2.49s |
| #346 | KAT Coder AIR V2.5 medium | Kwaipilot | 1 | 0.9 | $0.048 | 3/4 | 3.79s |
| #351 | MiniMax M2.7 medium | Minimax | 1 | 0.8 | $0.326 | 2/4 | 40.3s |
| #355 | Grok 4.20 Beta medium | X AI | 1 | 0.9 | $0.750 | 3/4 | 3.16s |
| #373 | DeepSeek V3.2 none | DeepSeek | 1 | 0.3 | $0.119 | 0/4 | 9.35s |
| #375 | Gemini 3.1 Flash Lite high | 1 | 0.9 | $2.044 | 3/4 | 37.2s | |
| #382 | Ling 2.6 Flash default | Inclusionai | 1 | 0.7 | $0.002 | 2/4 | 11.8s |