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: Muda wa majibu (wastani) ↓.

Modeli zilizoonyeshwa

Wastani wa Alama ya Mchanganyiko

6.2

Modeli bora

Gemini 3.1 Flash Lite Preview 10.0

Sababu za kushindwa

Kwa sababu ya kushindwa Jibu lisilo sahihi37 Kwa sababu ya kushindwa Mwito wa zana si sahihi10 Kwa sababu ya kushindwa Hitilafu ya API5 Kwa sababu ya kushindwa Muda umeisha2 Kwa sababu ya kushindwa Hakuna jibu1

Nafasi	Modeli	Kampuni	Alama ya Mchanganyiko	Alama	Majaribio sahihi	Muda wa majibu (wastani)
#11	Gemini 3.1 Flash Lite Preview high	Google	10.0	8.4	1/1	280.5s
#39	Seed-2.0-Mini medium	Bytedance Seed	10.0	7.5	1/1	262.8s
#10	Qwen3.5-27B medium	Qwen	10.0	8.4	1/1	164.0s
#64	DeepSeek V3.2 none	DeepSeek	6.5	6.1	0/1	115.9s
#19	Qwen3.5-122B-A10B medium	Qwen	10.0	8.1	1/1	107.8s
#27	DeepSeek V3.2 medium	DeepSeek	10.0	8.0	1/1	93.1s
#45	GPT-5 Mini medium	OpenAI	10.0	7.0	1/1	88.2s
#51	Nemotron 3 Super medium	NVIDIA	10.0	6.7	1/1	87.8s
#37	Claude Opus 4.6 medium	Anthropic	10.0	7.6	1/1	76.7s
#41	MiMo-V2-Flash medium	Xiaomi	9.8	7.5	1/1	75.7s
#43	Qwen3.5-35B-A3B medium	Qwen	4.7	7.4	0/1	75.3s
#24	Gemma 4 26B A4B medium	Google	9.6	8.0	1/1	73.5s
#46	Kimi K2.5 medium	Moonshot AI	10.0	7.0	1/1	71.4s
#57	GPT-5 Nano medium	OpenAI	10.0	6.3	1/1	66.0s
#93	GLM 4.7 Flash medium	Z.ai	2.8	4.6	0/1	65.6s

1 2 3 4 5 6 7

→

Orodha ya Mchanganyiko

Modeli bora kwa Alama ya Mchanganyiko

Alama ya Mchanganyiko dhidi ya jumla ya gharama

Modeli bora kwa Muda wa majibu (wastani)