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: Correcte tests ↓.
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 | |
| #3 | Claude Opus 4.7 medium | Anthropic | 1 | 9.2 | 16/18 | 3.53s |
| #4 | Claude Opus 4.7 none | Anthropic | 2 | 9.2 | 16/18 | 3.13s |
| #5 | Gemini 3 Flash Preview low | 3 | 8.8 | 15/18 | 6.01s | |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 2 | 8.5 | 14/18 | 46.6s |
| #12 | Gemini 3 PRO Preview medium | 3 | 8.4 | 14/18 | 9.06s | |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 3 | 8.5 | 13/17 | 13.9s |
| #11 | Gemini 3.1 Flash Lite Preview high | 3 | 8.4 | 12/16 | 68.8s | |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 3 | 8.6 | 13/18 | 30.4s |
| #7 | GPT-5.3-Codex medium | OpenAI | 3 | 8.6 | 13/18 | 15.4s |
| #10 | Qwen3.5-27B medium | Qwen | 1 | 8.4 | 13/18 | 53.0s |
| #13 | GLM 5 medium | Z.ai | 2 | 8.4 | 13/18 | 23.3s |
| #14 | Gemma 4 31B medium | 1 | 8.3 | 13/18 | 24.9s | |
| #15 | Gemini 2.5 Flash medium | 4 | 8.2 | 13/18 | 12.1s | |
| #16 | GPT-5.4 medium | OpenAI | 3 | 8.2 | 13/18 | 18.6s |