Kushindwa kwa kategoria za AI BENCHY
Utatuzi wa mafumbo: Hakufuata maelekezo
Utatuzi wa mafumbo
Hakufuata maelekezo
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Hakufuata maelekezo katika Utatuzi wa mafumbo, ili uone udhaifu haraka.
Sababu za kushindwa
| Nafasi | Modeli | Kampuni | Idadi ya Hakufuata maelekezo | Alama ya kategoria | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #45 | GPT-5 Mini medium | OpenAI | 1 | 5.6 | 1/3 | 14.1s |
| #46 | Kimi K2.5 medium | Moonshot AI | 1 | 5.3 | 1/3 | 45.4s |
| #48 | Gemma 4 31B none | 1 | 5.5 | 1/3 | 2.95s | |
| #50 | Hunter Alpha medium | OpenRouter | 1 | 6.1 | 1/3 | 5.36s |
| #52 | Grok 4.1 Fast medium | X AI | 1 | 5.3 | 1/3 | 8.08s |
| #55 | MiMo-V2-Omni none | Xiaomi | 1 | 8.0 | 2/3 | 2.71s |
| #57 | GPT-5 Nano medium | OpenAI | 1 | 5.3 | 1/3 | 19.8s |
| #58 | GLM 5V Turbo none | Z.ai | 1 | 5.3 | 1/3 | 2.22s |
| #59 | Qwen3.5-Flash none | Qwen | 1 | 3.3 | 0/3 | 5.90s |
| #60 | Gemma 4 26B A4B none | 1 | 5.7 | 1/3 | 739ms | |
| #62 | Gemini 2.5 Flash none | 1 | 5.7 | 1/3 | 576ms | |
| #63 | Qwen3.5-35B-A3B none | Qwen | 1 | 3.9 | 0/3 | 1.34s |
| #65 | MiMo-V2-Pro none | Xiaomi | 1 | 6.0 | 1/3 | 1.83s |
| #66 | GPT-5.4 none | OpenAI | 1 | 5.6 | 1/3 | 1.52s |
| #67 | Qwen3.5-27B none | Qwen | 1 | 6.7 | 1/3 | 1.37s |