AI BENCHY Categoriefouten
Algemene kennis: Verkeerd antwoord
Algemene kennis
Verkeerd antwoord
Zie welke AI-modellen op Algemene kennis het meest kans hebben op Verkeerd antwoord, zodat je zwakke punten sneller ziet.
Foutredenen
| Rang | Model | Bedrijf | Verkeerd antwoord-aantal | Categoriescore | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #106 | MiniMax M2.5 medium | Minimax | 1 | 3.0 | 0/1 | 80.8s |
| #107 | Mistral Small 4 medium | Mistral | 1 | 3.0 | 0/1 | 5.92s |
| #110 | Qwen3.5-122B-A10B none | Qwen | 1 | 3.0 | 0/1 | 295ms |
| #112 | Kimi K2.5 none | Moonshot AI | 1 | 3.0 | 0/1 | 3.90s |
| #114 | GLM 5 Turbo none | Z.ai | 1 | 3.0 | 0/1 | 2.37s |
| #118 | Ling-2.6-flash none | Inclusionai | 1 | 3.0 | 0/1 | 1.06s |
| #119 | gpt-oss-120b none | OpenAI | 1 | 3.0 | 0/1 | 47.3s |
| #120 | DeepSeek V4 Flash none | DeepSeek | 1 | 3.0 | 0/1 | 3.07s |
| #121 | Qwen3 Coder Next none | Qwen | 1 | 3.0 | 0/1 | 601ms |
| #122 | Nemotron 3 Super none | NVIDIA | 1 | 3.0 | 0/1 | 8.94s |
| #123 | MiniMax M2.7 medium | Minimax | 1 | 3.0 | 0/1 | 22.8s |
| #124 | Mistral Small 4 none | Mistral | 1 | 3.0 | 0/1 | 397ms |
| #125 | GPT-5.4 Mini none | OpenAI | 1 | 3.0 | 0/1 | 1.33s |
| #126 | Qwen3.6 35B A3B none | Qwen | 1 | 3.0 | 0/1 | 414ms |
| #127 | GPT-4o-mini none | OpenAI | 1 | 3.0 | 0/1 | 794ms |