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. Sortieren nach: Korrekte Tests ↓.
Fehlergründe
188/188
Modelle filtern
Keine Modelle entsprechen der aktuellen Suche und den Filtern.
| Rang | Modell | Unternehmen | Falsche Antwort-Anzahl | Kategorie-Score | Gesamtkosten | Korrekte Tests | Antwortzeit (Durchschnitt) |
|---|---|---|---|---|---|---|---|
| #5 | GPT-5.6 Sol low | OpenAI | 1 | 8.3 | $0.357 | 3/4 | 2.60s |
| #10 | GPT-5.6 Sol high | OpenAI | 1 | 8.7 | $0.446 | 3/4 | 3.39s |
| #18 | Seed 2.1 Turbo low | Bytedance Seed | 1 | 8.2 | $1.546 | 3/4 | 34.8s |
| #25 | GPT-5.3-Codex medium | OpenAI | 1 | 8.7 | $0.988 | 3/4 | 4.16s |
| #27 | Seed 2.1 Turbo high | Bytedance Seed | 1 | 8.2 | $1.797 | 3/4 | 47.0s |
| #33 | Gemini 3.6 Flash low | 1 | 8.7 | $0.251 | 3/4 | 1.85s | |
| #35 | Claude Opus 4.7 medium | Anthropic | 1 | 8.3 | $1.476 | 3/4 | 1.85s |
| #42 | GPT-5.4 medium | OpenAI | 1 | 8.3 | $1.560 | 3/4 | 4.11s |
| #49 | Seed 2.1 Turbo medium | Bytedance Seed | 1 | 8.2 | $1.951 | 3/4 | 28.2s |
| #53 | Gemini 2.5 Flash medium | 1 | 8.4 | $0.644 | 3/4 | 6.30s | |
| #61 | DeepSeek V4 Flash 0731 low | DeepSeek | 1 | 8.2 | $0.044 | 3/4 | 10.1s |
| #62 | DeepSeek V4 Flash 0731 high | DeepSeek | 1 | 8.7 | $0.084 | 3/4 | 13.6s |
| #65 | GPT-5.6 Terra high | OpenAI | 1 | 8.3 | $0.836 | 3/4 | 2.54s |
| #67 | GPT-5.2 Chat none | OpenAI | 1 | 8.7 | $0.594 | 3/4 | 3.40s |
| #74 | GPT-5.6 Terra medium | OpenAI | 1 | 8.3 | $0.523 | 3/4 | 2.22s |