AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Kushindwa kwa kategoria za AI BENCHY

Mchanganyiko: Mwito wa zana si sahihi

Mchanganyiko
Mwito wa zana si sahihi

Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Mwito wa zana si sahihi katika Mchanganyiko, ili uone udhaifu haraka. Panga kwa: Muda wa majibu (wastani) ↑.

Modeli zilizoonyeshwa

15

Jumla ya kushindwa

19

Modeli iliyoathirika zaidi

Granite 4.1 8B 1
Nafasi Modeli Kampuni Idadi ya Mwito wa zana si sahihi Alama ya kategoria Majaribio sahihi Muda wa majibu (wastani)
#163 Granite 4.1 8B none IBM Granite 1 3.0 0/1 1.88s
#122 GLM 4.7 Flash none Z.ai 1 3.0 0/1 3.22s
#32 Gemini 3.5 Flash minimal Google 1 3.0 0/1 3.56s
#128 Qwen3.6 Flash none Qwen 1 3.0 0/1 4.22s
#145 Laguna M.1 none Poolside 1 3.0 0/1 4.32s
#154 Qwen3.5-9B none Qwen 1 3.0 0/1 5.91s
#127 Grok 4.20 none X AI 1 3.0 0/1 6.04s
#106 Grok 4.20 Beta none X AI 1 3.0 0/1 6.48s
#118 Qwen3.6 27B none Qwen 1 3.0 0/1 9.95s
#59 GLM 5V Turbo medium Z.ai 1 6.9 0/1 15.1s
#112 GLM 5.1 none Z.ai 1 2.8 0/1 32.6s
#138 Ling-2.6-flash none Inclusionai 1 3.0 0/1 35.3s
#130 MiniMax M2.7 medium Minimax 1 4.7 0/1 41.0s
#119 Cobuddy medium Baidu 1 3.0 0/1 47.4s
#129 MiniMax M2.5 medium Minimax 1 4.5 0/1 60.4s

Modeli bora kwa Idadi ya Mwito wa zana si sahihi

Idadi ya Mwito wa zana si sahihi dhidi ya Alama

Modeli bora kwa Muda wa majibu (wastani)

Modeli bora kwa Gharama iliyopotezwa inayokadiriwa