Orodha ya modeli za Mchanganyiko

Kategoria ya AI BENCHY

Ona ni modeli gani za AI zinafanya vizuri zaidi katika Mchanganyiko, zipi zinabaki thabiti, na pengo kubwa liko wapi. Panga kwa: Majaribio sahihi ↑.

Modeli zilizoonyeshwa

Wastani wa Alama ya Mchanganyiko

6.3

Modeli bora

Sababu za kushindwa

Kwa sababu ya kushindwa Jibu lisilo sahihi52 Kwa sababu ya kushindwa Mwito wa zana si sahihi19 Kwa sababu ya kushindwa Hitilafu ya API13 Kwa sababu ya kushindwa Hakuna jibu2 Kwa sababu ya kushindwa Muda umeisha2 Kwa sababu ya kushindwa Hakufuata maelekezo1

Nafasi	Modeli	Kampuni	Alama ya Mchanganyiko	Alama	Majaribio sahihi	Muda wa majibu (wastani)
#77	Claude Sonnet 4.6 none	Anthropic	9.5	6.8	1/1	23.8s
#80	Mimo V2 Omni medium	Xiaomi	10.0	6.7	1/1	25.9s
#81	Mercury 2 medium	Inception	10.0	6.6	1/1	3.28s
#82	Hy3 preview high	Tencent	10.0	6.6	1/1	113.1s
#86	Grok 4.1 Fast medium	X AI	10.0	6.5	1/1	37.6s
#88	Qwen3.7 Plus none	Qwen	10.0	6.4	1/1	29.4s
#89	Hy3 preview low	Tencent	10.0	6.4	1/1	78.7s
#93	Qwen3.6 Plus Preview medium	Qwen	10.0	6.3	1/1	35.0s
#94	GPT-5 Nano medium	OpenAI	10.0	6.3	1/1	66.0s
#99	gpt-oss-120b medium	OpenAI	10.0	6.1	1/1	31.2s
#103	DeepSeek V4 Pro high	DeepSeek	10.0	6.0	1/1	65.0s
#105	Nemotron 3 Super medium	NVIDIA	10.0	5.8	1/1	87.8s
#113	DeepSeek V4 Pro none	DeepSeek	9.5	5.7	1/1	25.5s

Orodha ya Mchanganyiko