AI BENCHY Fouten
Verkeerd antwoord-fouten
Zie welke AI-modellen het vaakst tegen Verkeerd antwoord aanlopen, zodat je betrouwbaarheidsrisico's ziet voordat je kiest. Sorteren op: Responstijd (gem.) ↓.
Categorieën
| Rang | Model | Bedrijf | Verkeerd antwoord-aantal | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #97 | Qwen3.5-9B medium | Qwen | 1 | 4.4 | 3/18 | 73.6s |
| #46 | Kimi K2.5 medium | Moonshot AI | 4 | 7.0 | 9/18 | 72.4s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 2 | 7.5 | 11/18 | 69.7s |
| #11 | Gemini 3.1 Flash Lite Preview high | 3 | 8.4 | 12/16 | 68.8s | |
| #32 | Qwen3.5-Flash medium | Qwen | 1 | 7.8 | 11/18 | 66.7s |
| #10 | Qwen3.5-27B medium | Qwen | 1 | 8.4 | 13/18 | 53.0s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 2 | 8.5 | 14/18 | 46.6s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 3 | 8.0 | 12/18 | 46.4s |
| #34 | Kimi K2.6 medium | Moonshot AI | 2 | 7.7 | 11/18 | 45.2s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 2 | 7.4 | 10/18 | 44.5s |
| #57 | GPT-5 Nano medium | OpenAI | 7 | 6.3 | 7/18 | 44.1s |
| #71 | MiniMax M2.5 medium | Minimax | 5 | 5.7 | 5/18 | 39.6s |
| #93 | GLM 4.7 Flash medium | Z.ai | 8 | 4.6 | 4/18 | 32.3s |
| #19 | Qwen3.5-122B-A10B medium | Qwen | 3 | 8.1 | 13/18 | 31.4s |
| #80 | MiniMax M2.7 medium | Minimax | 5 | 5.3 | 4/18 | 31.1s |