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.) |
|---|---|---|---|---|---|---|
| #2 | Gemini 3.1 Pro Preview medium | 1 | 9.6 | 17/18 | 16.0s | |
| #7 | GPT-5.3-Codex medium | OpenAI | 3 | 8.6 | 13/18 | 15.4s |
| #20 | Qwen3.6 Plus medium | Qwen | 3 | 8.1 | 13/18 | 15.3s |
| #44 | GPT-5.4 Mini medium | OpenAI | 4 | 7.3 | 9/18 | 15.2s |
| #31 | GLM 5V Turbo medium | Z.ai | 3 | 7.8 | 11/18 | 15.0s |
| #40 | GPT-5.2 medium | OpenAI | 2 | 7.5 | 11/18 | 14.0s |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 3 | 8.5 | 13/17 | 13.9s |
| #76 | Kimi K2.5 none | Moonshot AI | 12 | 5.5 | 6/18 | 13.4s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 2 | 8.0 | 13/18 | 12.7s |
| #23 | MiMo-V2-Pro medium | Xiaomi | 3 | 8.1 | 12/18 | 12.3s |
| #15 | Gemini 2.5 Flash medium | 4 | 8.2 | 13/18 | 12.1s | |
| #64 | DeepSeek V3.2 none | DeepSeek | 8 | 6.1 | 7/18 | 12.1s |
| #84 | gpt-oss-120b none | OpenAI | 6 | 5.2 | 4/18 | 12.0s |
| #38 | GPT-5.4 Nano medium | OpenAI | 4 | 7.6 | 11/18 | 11.2s |
| #92 | Qwen3 Coder Next medium | Qwen | 9 | 4.7 | 3/18 | 10.8s |