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: Majaribio sahihi ↑.

Modeli zilizoonyeshwa

Wastani wa Alama ya Uchanganuzi na uchimbaji wa data

8.7

Modeli bora

MiMo-V2.5 2.7

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)
#29	Qwen3.5-122B-A10B medium	Qwen	10.0	7.8	2/2	23.4s
#30	Qwen3.5-27B medium	Qwen	10.0	7.8	2/2	30.3s
#31	DeepSeek V4 Flash high	DeepSeek	10.0	7.7	2/2	28.0s
#32	Gemini 3.5 Flash minimal	Google	10.0	7.7	2/2	1.66s
#34	Qwen3.7 Max none	Qwen	10.0	7.7	2/2	1.35s
#35	Gemini 3 PRO Preview medium	Google	10.0	7.6	2/2	10.8s
#36	Qwen3.5 Plus 2026-04-20 medium	Qwen	10.0	7.6	2/2	38.3s
#37	Gemma 4 26B A4B medium	Google	10.0	7.6	2/2	16.5s
#38	Grok 4.3 medium	X AI	10.0	7.6	2/2	19.0s
#39	Qwen3.6 Flash medium	Qwen	10.0	7.5	2/2	9.65s
#40	Gemini 3.1 Flash Lite Preview medium	Google	10.0	7.5	2/2	2.29s
#41	Nemotron 3 Ultra 550b A55b medium	NVIDIA	10.0	7.5	2/2	5.68s
#42	GPT-5.2 medium	OpenAI	10.0	7.5	2/2	3.15s
#44	Gemini 3.1 Flash Lite medium	Google	10.0	7.5	2/2	2.60s
#45	GPT-5.4 Mini medium	OpenAI	10.0	7.5	2/2	2.43s

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)