AI BENCHY Fouten
API-fout-fouten
Zie welke AI-modellen het vaakst tegen API-fout aanlopen, zodat je betrouwbaarheidsrisico's ziet voordat je kiest. Sorteren op: Correcte tests ↓.
Categorieën
In categorie Programmeren43 In categorie Gegevensparsering en extractie16 In categorie Toolaanroepen15 In categorie Anti-AI-trucs13 In categorie Gecombineerd13 In categorie Puzzeloplossing13 In categorie Algemene intelligentie12 In categorie Algemene kennis12 In categorie Domeinspecifiek6 In categorie Instructies opvolgen1
| Rang | Model | Bedrijf | API-fout-aantal | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #20 | Gemini 3.5 Flash none | 3 | 8.1 | 15/21 | 9.93s | |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 7.9 | 14/21 | 73.8s |
| #26 | Qwen3.6 Plus medium | Qwen | 1 | 7.9 | 14/21 | 30.7s |
| #27 | Gemma 4 31B medium | 2 | 7.8 | 14/21 | 56.5s | |
| #33 | Hy3 preview medium | Tencent | 3 | 7.7 | 14/21 | 16.3s |
| #35 | Gemini 3 PRO Preview medium | 4 | 7.6 | 14/21 | 9.05s | |
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 1 | 7.5 | 13/21 | 15.1s |
| #46 | Qwen3.6 35B A3B medium | Qwen | 2 | 7.4 | 13/21 | 18.1s |
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 1 | 7.5 | 12/21 | 26.1s |
| #49 | Qwen3.5-Flash medium | Qwen | 1 | 7.4 | 12/21 | 63.3s |
| #51 | Mimo V2 PRO medium | Xiaomi | 1 | 7.4 | 12/21 | 22.2s |
| #55 | GLM 5.1 medium | Z.ai | 1 | 7.3 | 12/21 | 33.7s |
| #64 | MiMo-V2-Flash medium | Xiaomi | 1 | 7.2 | 12/21 | 20.1s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 1 | 7.1 | 11/21 | 72.6s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 2 | 7.0 | 11/21 | 68.7s |