AI BENCHY Compare

Google: Gemma 4 31B vs Z.ai: GLM 5

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-05-19

Kipimo	Gemma 4 31B Gemma 4 31B medium Toleo: 2026-04-02 Inapatikana bure	GLM 5 GLM 5 medium Toleo: 2026-02-12

Kipimo	Gemma 4 31B Gemma 4 31B medium Toleo: 2026-04-02 Inapatikana bure	GLM 5 GLM 5 medium Toleo: 2026-02-12
Alama	8.2	8.1
Nafasi	#18	#24
Uaminifu	6.7	10.0
Uthabiti	9.6	8.3
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio	77.2%	80.7%
Majaribio yasiyo thabiti	1	4
Jumla ya uendeshaji	57	57
Gharama kwa matokeo	0.158	1.379
Jumla ya gharama	$0.023	$0.180
Bei ya ingizo	$0.120 / 1M	$0.600 / 1M
Bei ya toleo	$0.370 / 1M	$1.920 / 1M
Tokeni za matokeo	14,426	20,564
Tokeni za hoja	37,964	70,787
Muda wa majibu (wastani)	28.72s	27.34s
Muda wa majibu (upeo)	90.14s	79.09s
Muda wa majibu (jumla)	488.27s	300.78s

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
Gemma 4 31B	10.0	10.0	100.0%	0		12.89s	962	2,046
GLM 5	10.0	10.0	100.0%	0		23.66s	480	7,056

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
Gemma 4 31B	4.7	1.6	66.7%	1		70.97s	3,166	5,449
GLM 5	10.0	10.0	100.0%	0		79.09s	330	19,814

Mchanganyiko	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za matokeo	Tokeni za hoja
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0
GLM 5	10.0	10.0	100.0%	0		28.96s	662	3,242

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
Gemma 4 31B	10.0	10.0	100.0%	0		21.11s	1,822	2,951
GLM 5	7.1	5.6	83.3%	1		8.90s	567	3,734

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
Gemma 4 31B	7.7	10.0	66.7%	0		38.48s	4,349	8,985
GLM 5	3.5	4.4	33.3%	2		0ms	13,176	14,137

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
Gemma 4 31B	10.0	10.0	100.0%	0		9.57s	105	888
GLM 5	6.1	3.1	66.7%	1		14.69s	2,020	2,248

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
Gemma 4 31B	10.0	10.0	100.0%	0		12.76s	533	2,035
GLM 5	10.0	10.0	100.0%	0		7.25s	1,001	2,129

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
Gemma 4 31B	9.9	10.0	100.0%	0		27.63s	1,797	5,596
GLM 5	10.0	10.0	100.0%	0		15.64s	1,694	4,983

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
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0
GLM 5	10.0	10.0	100.0%	0		15.93s	233	994

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
Gemma 4 31B	3.0	10.0	0.0%	0		90.14s	1,692	10,014
GLM 5	3.0	10.0	0.0%	0		67.37s	401	12,450

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Gemini 3.5 FlashminimalvsGLM 5medium Gemini 3 Flash PreviewnonevsGLM 5medium Gemini 3.1 Flash Lite PreviewlowvsGLM 5medium Gemini 3.1 Flash Lite PreviewnonevsGLM 5medium GPT-5.2 ChatnonevsGLM 5medium Gemini 3.1 Flash LitelowvsGLM 5medium GPT-5.3 ChatnonevsGLM 5medium DeepSeek V4 FlashhighInapatikana burevsGLM 5medium Gemma 4 31BmediumInapatikana burevsGPT-5.2 Chatnone Gemma 4 31BmediumInapatikana burevsGPT-5.5low Gemma 4 31BmediumInapatikana burevsGPT-5.3 Chatnone DeepSeek V4 FlashhighInapatikana burevsGemma 4 31BmediumInapatikana bure