AI BENCHY Kategoriefehler
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
| Rang | Modell | Unternehmen | Falsche Antwort-Anzahl | Kategorie-Score | Korrekte Tests | Antwortzeit (Durchschnitt) |
|---|---|---|---|---|---|---|
| #78 | Qwen3.6 27B medium | Qwen | 1 | 8.3 | 3/4 | 12.6s |
| #81 | Mercury 2 medium | Inception | 1 | 6.9 | 2/4 | 1.12s |
| #84 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 6.9 | 2/4 | 3.46s |
| #86 | Grok 4.1 Fast medium | X AI | 1 | 8.7 | 3/4 | 3.81s |
| #87 | Gemini 3.1 Flash Lite minimal | 1 | 8.3 | 3/4 | 1.10s | |
| #92 | Laguna M.1 medium | Poolside | 1 | 6.5 | 2/4 | 4.87s |
| #99 | gpt-oss-120b medium | OpenAI | 1 | 6.7 | 2/4 | 10.2s |
| #100 | Grok Build 0.1 none | X AI | 1 | 8.7 | 3/4 | 6.30s |
| #102 | Gemma 4 26B A4B none | 1 | 8.3 | 3/4 | 1.28s | |
| #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 |
| #119 | Cobuddy medium | Baidu | 1 | 8.7 | 3/4 | 10.00s |
| #126 | gpt-oss-120b none | OpenAI | 1 | 6.5 | 2/4 | 32.8s |
| #130 | MiniMax M2.7 medium | Minimax | 1 | 7.9 | 2/4 | 40.3s |
| #133 | DeepSeek V3.2 none | DeepSeek | 1 | 3.2 | 0/4 | 9.35s |