Orodha ya modeli za Uchanganuzi na uchimbaji wa data

Kategoria ya AI BENCHY

Ona ni modeli gani za AI zinafanya vizuri zaidi katika Uchanganuzi na uchimbaji wa data, zipi zinabaki thabiti, na pengo kubwa liko wapi. Panga kwa: Muda wa majibu (wastani) ↓.

Modeli zilizoonyeshwa

Wastani wa Alama ya Uchanganuzi na uchimbaji wa data

8.7

Modeli bora

Qwen3.5-9B 3.6

Sababu za kushindwa

Kwa sababu ya kushindwa Jibu lisilo sahihi35 Kwa sababu ya kushindwa Hitilafu ya API16 Kwa sababu ya kushindwa Hakuna jibu5 Kwa sababu ya kushindwa Muundo wa ziada4 Kwa sababu ya kushindwa Muda umeisha1

Nafasi	Modeli	Kampuni	Alama ya Uchanganuzi na uchimbaji wa data	Alama	Majaribio sahihi	Muda wa majibu (wastani)
#31	DeepSeek V4 Flash high	DeepSeek	10.0	7.7	2/2	28.0s
#73	Seed-2.0-Mini medium	Bytedance Seed	10.0	6.9	2/2	24.3s
#139	DeepSeek V4 Flash none	DeepSeek	10.0	5.0	2/2	23.8s
#103	DeepSeek V4 Pro high	DeepSeek	7.3	6.0	1/2	23.6s
#29	Qwen3.5-122B-A10B medium	Qwen	10.0	7.8	2/2	23.4s
#79	Hunter Alpha medium	OpenRouter	10.0	6.7	2/2	23.2s
#130	MiniMax M2.7 medium	Minimax	6.3	5.3	1/2	21.9s
#18	Qwen3.7 Plus medium	Qwen	10.0	8.2	2/2	21.7s
#111	Owl Alpha medium	Openrouter	10.0	5.7	2/2	21.6s
#94	GPT-5 Nano medium	OpenAI	3.7	6.3	0/2	21.4s
#27	Gemma 4 31B medium	Google	10.0	7.8	2/2	21.1s
#60	Kimi K2.6 medium	Moonshot AI	10.0	7.2	2/2	20.4s
#152	MiMo-V2-Flash none	Xiaomi	2.9	4.6	0/2	19.7s
#38	Grok 4.3 medium	X AI	10.0	7.6	2/2	19.0s
#43	MiMo-V2.5-Pro medium	Xiaomi	7.3	7.5	1/2	18.8s

Orodha ya Uchanganuzi na uchimbaji wa data

Modeli bora kwa Alama ya Uchanganuzi na uchimbaji wa data

Alama ya Uchanganuzi na uchimbaji wa data dhidi ya jumla ya gharama

Modeli bora kwa Muda wa majibu (wastani)