Granite 4.1 8b (default) vs gpt-oss-120b

Modeli zilizolinganishwa

Nafasi: #366
Jumla ya tokeni za matokeo: 5,996
Muda wa majibu (wastani): 1.38s
Jumla ya gharama: $0.007

Nafasi: #356
Jumla ya tokeni za matokeo: 62,213
Muda wa majibu (wastani): 28.63s
Jumla ya gharama: $0.016

Muundo unaopendekezwa Granite 4.1 8b (default)

Its score stays close to the best score here (3.8 vs 4.2), while costing about 2.5x less than gpt-oss-120b.

Ulinganisho wa kina

Kipimo	Granite 4.1 8b Granite 4.1 8b default Toleo: 2026-05-01	gpt-oss-120b gpt-oss-120b none Toleo: 2025-08-05

Kipimo	Granite 4.1 8b Granite 4.1 8b default Toleo: 2026-05-01	gpt-oss-120b gpt-oss-120b none Toleo: 2025-08-05
Alama	3.8	4.2
Nafasi	#366	#356
Uaminifu	10.0	10.0
Uthabiti	10.0	7.6
Majaribio	69/69	60/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio	8.7%	34.8%
Majaribio yasiyo thabiti	0	3
Jumla ya uendeshaji	69	60
Gharama kwa matokeo	0.315	0.274
Jumla ya gharama	$0.007	$0.016
Bei ya ingizo	$0.050 / 1M	$0.037 / 1M
Bei ya toleo	$0.100 / 1M	$0.170 / 1M
Bei ya kusoma akiba	Haipo	Haipo
Bei ya kuandika akiba	Haipo	Haipo
Jumla ya tokeni za ingizo	113,836	131,652
Tokeni za matokeo	5,996	16,869
Tokeni za hoja	0	53,081
Muda wa majibu (wastani)	1.38s	28.63s
Muda wa majibu (upeo)	16.67s	140.90s
Muda wa majibu (jumla)	31.81s	486.69s
Vigezo	8B	117B jumla (5.1B vinavyotumika)
Upatikanaji	Chanzo huria	Chanzo huria

Bei za akiba zinahusu tokeni za ingizo. Kusoma hutumia tena maelekezo yaliyohifadhiwa; kuandika huyahifadhi na kunaweza kuongeza gharama. Tokeni za matokeo hutumia bei ya matokeo.

Onyesho la kizazi cha modeli

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#366 Granite 4.1 8b

default

Gharama: $0.001
Muda: 3.2s
Tokeni: 491 tok

#356 gpt-oss-120b

none

Hakuna matokeo ya onyesho yaliyozalishwa kwa modeli hii bado.

Gharama: Haipo
Muda: -
Tokeni: 0 tok

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

Kategoria:

Kazi za mawakala	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.0	10.0	0.0%	0		60ms	0	0	0
gpt-oss-120b	6.1	3.1	66.7%	1		140.90s	122,571	145	10,404

Mbinu za kupinga AI	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	4.9	10.0	25.0%	0		844ms	645	903	0
gpt-oss-120b	6.5	10.0	50.0%	0		32.84s	1,336	5,685	2,991

Uandishi wa msimbo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	4.5	10.0	0.0%	0		775ms	8,344	525	0
gpt-oss-120b	1.5	0.4	22.2%	1		9.57s	901	204	3,028

Mchanganyiko	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.0	10.0	0.0%	0		9.28s	86,631	3,481	0
gpt-oss-120b	1.5	5.0	0.0%	0		0ms	0	0	0

Uchanganuzi na uchimbaji wa data	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.0	10.0	0.0%	0		575ms	7,617	195	0
gpt-oss-120b	6.5	10.0	50.0%	0		7.12s	2,421	149	449

Mahususi kwa domeni	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.0	10.0	0.0%	0		287ms	777	24	0
gpt-oss-120b	3.0	10.0	0.0%	0		34.98s	1,294	4,675	25,774

Akili ya jumla	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	4.0	10.0	0.0%	0		499ms	528	115	0
gpt-oss-120b	4.8	10.0	0.0%	0		10.79s	584	615	684

Ufuataji wa maagizo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.6	9.9	0.0%	0		344ms	687	66	0
gpt-oss-120b	9.8	10.0	100.0%	0		5.06s	1,043	157	1,783

Utatuzi wa mafumbo	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.2	10.0	0.0%	0		608ms	672	432	0
gpt-oss-120b	6.0	7.2	55.6%	1		8.21s	1,188	2,101	1,881

Mwito wa zana	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	10.0	10.0	100.0%	0		2.17s	7,719	243	0
gpt-oss-120b	3.0	10.0	0.0%	0		0ms	0	0	0

Maarifa ya jumla	Alama	Uthabiti	Kiwango cha kupita kwa kila jaribio	Majaribio yasiyo thabiti	Majaribio sahihi	Muda wa majibu (wastani)	Tokeni za ingizo	Tokeni za matokeo	Tokeni za hoja
Granite 4.1 8b	3.0	10.0	0.0%	0		306ms	216	12	0
gpt-oss-120b	3.0	10.0	0.0%	0		47.29s	314	3,138	6,087

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Granite 4.1 8bdefaultvsNemotron 3.5 LightningnoneInapatikana bure gpt-oss-120bnonevsGLM 4.7 Flashmedium Granite 4.1 8bdefaultvsLing 3.0 Tinyhigh MiniMax M2.5mediumvsgpt-oss-120bnone gpt-oss-120bnonevsQwen3.5-9Bmedium Granite 4.1 8bdefaultvsLing 3.0 Tinylow Granite 4.1 8bdefaultvsLing 3.0 Tinymedium CobuddymediumInapatikana burevsgpt-oss-120bnone Granite 4.1 8bdefaultvsQwen3.5-9Bmedium Trinity Large PreviewdefaultInapatikana burevsgpt-oss-120bnone KAT Coder AIR V2.5defaultvsgpt-oss-120bnone Granite 4.1 8bdefaultvsMercury 2.5none