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.) |
|---|---|---|---|---|---|---|
| #88 | Nemotron 3 Super none | NVIDIA | 10 | 5.1 | 4/18 | 8.54s |
| #12 | Gemini 3 PRO Preview medium | 3 | 8.4 | 14/18 | 9.06s | |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 3 | 6.4 | 7/18 | 9.80s |
| #25 | Grok 4.20 Beta medium | X AI | 3 | 8.0 | 12/18 | 9.81s |
| #87 | Qwen3 Coder Next none | Qwen | 12 | 5.1 | 4/18 | 10.2s |
| #47 | Grok 4.20 medium | X AI | 3 | 7.0 | 9/18 | 10.3s |
| #50 | Hunter Alpha medium | OpenRouter | 4 | 6.7 | 8/18 | 10.3s |
| #92 | Qwen3 Coder Next medium | Qwen | 9 | 4.7 | 3/18 | 10.8s |
| #38 | GPT-5.4 Nano medium | OpenAI | 4 | 7.6 | 11/18 | 11.2s |
| #84 | gpt-oss-120b none | OpenAI | 6 | 5.2 | 4/18 | 12.0s |
| #64 | DeepSeek V3.2 none | DeepSeek | 8 | 6.1 | 7/18 | 12.1s |
| #15 | Gemini 2.5 Flash medium | 4 | 8.2 | 13/18 | 12.1s | |
| #23 | MiMo-V2-Pro medium | Xiaomi | 3 | 8.1 | 12/18 | 12.3s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 2 | 8.0 | 13/18 | 12.7s |
| #76 | Kimi K2.5 none | Moonshot AI | 12 | 5.5 | 6/18 | 13.4s |