Urambazaji
Advertise here

Modeli zilizolinganishwa

Ulinganisho wa benchmark GPT-6.1 Sol (xhigh) vs GPT-6 Astra (xhigh) vs Claude Sonnet 5.5 (xhigh): GPT-6.1 Sol (xhigh) inaongoza kwenye Alama kwa 9.9. GPT-6.1 Sol (xhigh) inaongoza kwenye Uaminifu kwa 10.0. GPT-6.1 Sol (xhigh) ina Jumla ya gharama ya chini zaidi kwa $1.377. Claude Sonnet 5.5 (xhigh) ndiyo ya haraka zaidi kwa 14.98s.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-11-18

Modeli zilizolinganishwa

Nafasi
#16
Jumla ya tokeni za matokeo
102,482
Muda wa majibu (wastani)
33.11s
Jumla ya gharama
$1.377
Nafasi
#18
Jumla ya tokeni za matokeo
90,095
Muda wa majibu (wastani)
29.67s
Jumla ya gharama
$6.213
Nafasi
#115
Jumla ya tokeni za matokeo
83,041
Muda wa majibu (wastani)
14.98s
Jumla ya gharama
$1.516
Muundo unaopendekezwa GPT-6.1 Sol (xhigh)

It has the best score here (9.9), while costing about 2.8x less than miundo mingine katika ulinganisho huu.

Ulinganisho wa kina

Kipimo GPT-6.1 Sol GPT-6.1 Sol xhigh Toleo: 2026-09-29 GPT-6 Astra GPT-6 Astra xhigh Toleo: 2026-09-04 Claude Sonnet 5.5 Claude Sonnet 5.5 xhigh Toleo: 2026-09-29
Alama 9.9 9.9 8.6
Nafasi #16 #18 #115
Uaminifu 10.0 9.9 10.0
Uthabiti 9.6 9.6 8.7
Majaribio 69/69 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 97.1% 97.1% 79.7%
Majaribio yasiyo thabiti 1 1 4
Jumla ya uendeshaji 69 69 69
Gharama kwa matokeo 6.256 28.237 9.473
Jumla ya gharama $1.377 $6.213 $1.516
Bei ya ingizo $2.000 / 1M $10.000 / 1M $2.000 / 1M
Bei ya toleo $10.000 / 1M $50.000 / 1M $10.000 / 1M
Bei ya kusoma akiba $0.100 / 1M $1.000 / 1M $0.200 / 1M
Bei ya kuandika akiba $2.500 / 1M $12.500 / 1M $2.500 / 1M
Jumla ya tokeni za ingizo 175,712 170,731 342,579
Tokeni za matokeo 5,640 5,865 12,848
Tokeni za hoja 96,842 84,230 70,193
Muda wa majibu (wastani) 33.11s 29.67s 14.98s
Muda wa majibu (upeo) 491.85s 381.11s 54.92s
Muda wa majibu (jumla) 761.52s 682.42s 344.60s
Vigezo ~2T jumla (~150B vinavyotumika) ~2T jumla (~150B vinavyotumika) ~1T jumla (~100B vinavyotumika)
Upatikanaji Imefungwa Imefungwa Imefungwa

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.

#16 GPT-6.1 Sol

xhigh
Gharama
$0.147
Muda
279.4s
Tokeni
14,790 tok

#18 GPT-6 Astra

xhigh
Gharama
$0.694
Muda
257.5s
Tokeni
13,964 tok

#115 Claude Sonnet 5.5

xhigh
Gharama
$0.319
Muda
258.6s
Tokeni
31,969 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

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
GPT-6.1 Sol 10.0 10.0 100.0% 0 10.65s 7,302 393 4,483
GPT-6 Astra 10.0 10.0 100.0% 0 8.27s 7,302 396 4,031
Claude Sonnet 5.5 8.2 7.2 88.9% 1 11.90s 10,608 555 9,501

Badilisha jozi ya ulinganisho