AI BENCHY Compare

OpenAI: GPT-5.2 Chat vs Qwen: Qwen3.6 Plus

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-05-10

Kipimo	GPT-5.2 Chat GPT-5.2 Chat none Toleo: 2025-12-11	Qwen3.6 Plus Qwen3.6 Plus medium Toleo: 2026-04-20

Kipimo	GPT-5.2 Chat GPT-5.2 Chat none Toleo: 2025-12-11	Qwen3.6 Plus Qwen3.6 Plus medium Toleo: 2026-04-20
Alama	7.6	7.9
Nafasi	#41	#28
Uaminifu	10.0	10.0
Uthabiti	8.8	9.6
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio	71.9%	70.2%
Majaribio yasiyo thabiti	3	1
Jumla ya uendeshaji	57	57
Gharama kwa matokeo	2.572	0.118
Jumla ya gharama	$0.309	$0.016
Bei ya ingizo	$1.750 / 1M	$0.325 / 1M
Bei ya toleo	$14.000 / 1M	$1.950 / 1M
Tokeni za matokeo	18,585	1,784
Tokeni za hoja	0	91,543
Muda wa majibu (wastani)	6.85s	17.06s
Muda wa majibu (upeo)	38.52s	47.51s
Muda wa majibu (jumla)	130.06s	307.07s

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

Muda wa majibu (wastani)

Alama vs Muda wa majibu (wastani)

Jumla ya tokeni za matokeo

Alama vs Jumla ya tokeni za matokeo

Mgawanyo wa kategoria

Mbinu za kupinga AI	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	8.7	7.9	91.7%	1		3.40s	1,807	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		9.90s	207	7,557

Uandishi wa msimbo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	10.0	10.0	100.0%	0		8.97s	1,345	0
Qwen3.6 Plus	3.0	10.0	0.0%	0		0ms	0	0

Mchanganyiko	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	10.0	10.0	100.0%	0		9.12s	1,243	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		34.95s	452	13,073

Uchanganuzi na uchimbaji wa data	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	10.0	10.0	100.0%	0		3.05s	980	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		14.95s	270	10,706

Mahususi kwa domeni	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	5.3	10.0	33.3%	0		17.78s	7,810	0
Qwen3.6 Plus	2.9	7.2	11.1%	1		29.59s	56	33,464

Akili ya jumla	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	4.4	3.0	33.3%	1		3.20s	335	0
Qwen3.6 Plus	5.1	10.0	0.0%	0		27.05s	111	5,232

Ufuataji wa maagizo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	7.3	5.9	83.3%	1		5.46s	1,528	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		7.54s	102	5,552

Utatuzi wa mafumbo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	7.7	10.0	66.7%	0		4.42s	1,743	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		6.11s	298	6,868

Mwito wa zana	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	10.0	10.0	100.0%	0		4.68s	555	0
Qwen3.6 Plus	10.0	10.0	100.0%	0		5.87s	267	1,330

Maarifa ya jumla	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
GPT-5.2 Chat	3.0	10.0	0.0%	0		6.89s	1,239	0
Qwen3.6 Plus	3.0	10.0	0.0%	0		47.51s	21	7,761

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Kimi K2.6mediumvsGPT-5.2 Chatnone GPT-5.2 ChatnonevsStep 3.5 Flashmedium Gemini 3.1 Flash LitelowvsGPT-5.2 Chatnone Gemini 3 Flash PreviewnonevsQwen3.6 Plusmedium GPT-5.2 ChatnonevsQwen3.5-Flashmedium Gemini 3.1 Flash Lite PreviewlowvsQwen3.6 Plusmedium Gemma 4 26B A4BmediumInapatikana burevsGPT-5.2 Chatnone GPT-5.2 ChatnonevsGLM 5.1medium GPT-5.2 ChatnonevsMiMo-V2-Promedium DeepSeek V4 FlashhighvsGPT-5.2 Chatnone GPT-5.2 ChatnonevsGLM 5V Turbomedium GPT-5.2 ChatnonevsQwen3.6 Flashmedium