Eșecuri pe categorii AI BENCHY
Apelare instrumente: Eroare API
Apelare instrumente
Eroare API
Vezi ce modele AI au cele mai mari șanse să întâmpine Eroare API la Apelare instrumente, ca să găsești mai repede punctele slabe.
Motive de eșec
| Rang | Model | Companie | Număr de Eroare API | Scor de categorie | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|
| #20 | Gemini 3.5 Flash none | 1 | 3.0 | 0/1 | 0ms | |
| #27 | Gemma 4 31B medium | 1 | 3.0 | 0/1 | 0ms | |
| #46 | Qwen3.6 35B A3B medium | Qwen | 1 | 3.0 | 0/1 | 0ms |
| #55 | GLM 5.1 medium | Z.ai | 1 | 3.0 | 0/1 | 0ms |
| #83 | Step 3.5 Flash none | Stepfun | 1 | 3.0 | 0/1 | 0ms |
| #84 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 3.0 | 0/1 | 0ms |
| #85 | Gemma 4 31B none | 1 | 3.0 | 0/1 | 0ms | |
| #89 | Hy3 preview low | Tencent | 1 | 2.8 | 0/1 | 17.8s |
| #96 | Ring-2.6-1T none | Inclusionai | 1 | 3.0 | 0/1 | 0ms |
| #100 | Grok Build 0.1 none | X AI | 1 | 3.0 | 0/1 | 0ms |
| #126 | gpt-oss-120b none | OpenAI | 1 | 3.0 | 0/1 | 0ms |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 3.0 | 0/1 | 0ms |
| #153 | Qwen3.6 35B A3B none | Qwen | 1 | 3.0 | 0/1 | 0ms |
| #160 | LFM2-24B-A2B none | Liquid | 1 | 3.0 | 0/1 | 0ms |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 1 | 3.0 | 0/1 | 0ms |