AI BENCHY Fouten
Geen antwoord-fouten
Zie welke AI-modellen het vaakst tegen Geen antwoord aanlopen, zodat je betrouwbaarheidsrisico's ziet voordat je kiest.
| Rang | Model | Bedrijf | Geen antwoord-aantal | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #71 | Step 3.7 Flash high | Stepfun | 4 | 7.0 | 11/21 | 64.5s |
| #78 | Qwen3.6 27B medium | Qwen | 3 | 6.8 | 10/21 | 59.7s |
| #158 | GLM 4.7 Flash medium | Z.ai | 3 | 4.4 | 4/21 | 35.1s |
| #37 | Gemma 4 26B A4B medium | 2 | 7.6 | 14/21 | 63.4s | |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 2 | 7.1 | 11/21 | 72.6s |
| #76 | Kimi K2.5 medium | Moonshot AI | 2 | 6.8 | 10/21 | 98.4s |
| #80 | Mimo V2 Omni medium | Xiaomi | 2 | 6.7 | 10/21 | 41.2s |
| #107 | Laguna Xs.2 medium | Poolside | 2 | 5.8 | 6/19 | 6.73s |
| #161 | Qwen3.5-9B medium | Qwen | 2 | 4.2 | 3/21 | 82.2s |
| #10 | Claude Opus 4.8 medium | Anthropic | 1 | 8.7 | 17/21 | 9.66s |
| #17 | GLM 5 medium | Z.ai | 1 | 8.3 | 15/21 | 33.5s |
| #22 | Step 3.7 Flash medium | Stepfun | 1 | 8.0 | 14/21 | 20.4s |
| #23 | GLM 5 Turbo medium | Z.ai | 1 | 8.0 | 14/21 | 23.0s |
| #27 | Gemma 4 31B medium | 1 | 7.8 | 14/21 | 56.5s | |
| #42 | GPT-5.2 medium | OpenAI | 1 | 7.5 | 13/21 | 16.9s |