AI BENCHY Compare

Google: Gemma 4 31B vs Inception: Mercury 2

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-02

Kipimo	Gemma 4 31B Gemma 4 31B none Toleo: 2026-04-02	Mercury 2 Mercury 2 medium Toleo: 2026-02-24

Kipimo	Gemma 4 31B Gemma 4 31B none Toleo: 2026-04-02	Mercury 2 Mercury 2 medium Toleo: 2026-02-24
Alama	6.7	6.3
Nafasi	#47	#51
Uthabiti	10.0	8.5
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio	52.9%	51.0%
Majaribio yasiyo thabiti	0	3
Jumla ya uendeshaji	51	51
Gharama kwa matokeo	0.023	0.634
Jumla ya gharama	$0.002	$0.045
Bei ya ingizo	$0.140 / 1M	$0.250 / 1M
Bei ya toleo	$0.400 / 1M	$0.750 / 1M
Tokeni za matokeo	660	3,723
Tokeni za hoja	0	46,120
Muda wa majibu (wastani)	2.55s	2.25s
Muda wa majibu (upeo)	4.68s	14.63s
Muda wa majibu (jumla)	38.20s	35.99s

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	6.5	10.0	50.0%	0		1.85s	45	0
Mercury 2	6.9	9.9	50.0%	0		1.12s	2,546	2,609

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
Mercury 2	10.0	10.0	100.0%	0		3.28s	268	4,887

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		2.25s	285	0
Mercury 2	7.3	5.9	83.3%	1		1.11s	183	1,656

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		3.22s	27	0
Mercury 2	2.9	7.2	11.1%	1		6.48s	41	30,754

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		2.09s	117	0
Mercury 2	4.8	10.0	0.0%	0		821ms	137	542

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	6.5	10.0	50.0%	0		2.84s	78	0
Mercury 2	10.0	10.0	100.0%	0		1.07s	14	958

Puzzle Solving	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	5.5	10.0	33.3%	0		2.95s	108	0
Mercury 2	3.9	7.5	22.2%	1		934ms	354	2,758

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
Mercury 2	10.0	10.0	100.0%	0		1.89s	180	1,956

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V3.2nonevsMercury 2medium Gemma 4 31BnonevsGPT-5 Minimedium Mercury 2mediumvsMiMo-V2-Omninone Gemma 4 31BnonevsNemotron 3 SupermediumInapatikana bure Gemma 4 31BnonevsGrok 4.1 Fastmedium Gemma 4 31BnonevsHunter Alphamedium Mercury 2mediumvsQwen3.5-Flashnone Mercury 2mediumvsGLM 5V Turbonone Seed-2.0-LitenonevsMercury 2medium Gemma 4 31BnonevsGPT-5.4 Minimedium Gemma 4 31BnonevsGrok 4.20medium Gemini 2.5 FlashnonevsMercury 2medium