Urambazaji
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Modeli zilizolinganishwa

Ulinganisho wa benchmark Inkling (high) vs DaisyRose 27B (xhigh) vs Qwen3.8 27B (high): Qwen3.8 27B (high) inaongoza kwenye Alama kwa 8.7. Inkling (high) inaongoza kwenye Uaminifu kwa 10.0. Qwen3.8 27B (high) ina Jumla ya gharama ya chini zaidi kwa ~$0.298. Inkling (high) ndiyo ya haraka zaidi kwa 62.72s.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-11-22

Modeli zilizolinganishwa

Nafasi
#136
Jumla ya tokeni za matokeo
249,242
Muda wa majibu (wastani)
62.72s
Jumla ya gharama
$1.238
Nafasi
#160
Jumla ya tokeni za matokeo
799,132
Muda wa majibu (wastani)
111.38s
Jumla ya gharama
$1.559
Nafasi
#104
Jumla ya tokeni za matokeo
677,080
Muda wa majibu (wastani)
166.34s
Jumla ya gharama
~$0.298
Muundo unaopendekezwa Qwen3.8 27B (high)

It has the best score here (8.7), while costing about 4.7x less than miundo mingine katika ulinganisho huu.

Ulinganisho wa kina

Kipimo Inkling Inkling high Toleo: 2026-07-18 Inapatikana bure DaisyRose 27B DaisyRose 27B xhigh Toleo: 2026-11-18 Qwen3.8 27B Qwen3.8 27B high Toleo: 2026-08-14 Inapatikana bure
Alama 8.4 8.1 8.7
Nafasi #136 #160 #104
Uaminifu 10.0 9.7 9.7
Uthabiti 9.0 8.9 9.2
Majaribio 69/69 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 78.3% 68.1% 78.3%
Majaribio yasiyo thabiti 3 3 2
Jumla ya uendeshaji 69 69 69
Gharama kwa matokeo 7.812 11.133 ~1.751
Jumla ya gharama $1.238 $1.559 ~$0.298
Bei ya ingizo $0.950 / 1M $0.150 / 1M Haipo
Bei ya toleo $4.050 / 1M $1.875 / 1M Haipo
Bei ya kusoma akiba $0.160 / 1M $0.038 / 1M Haipo
Bei ya kuandika akiba Haipo Haipo Haipo
Jumla ya tokeni za ingizo 240,395 401,324 348,967
Tokeni za matokeo 7,169 8,843 1,005
Tokeni za hoja 242,073 790,289 676,075
Muda wa majibu (wastani) 62.72s 111.38s 166.34s
Muda wa majibu (upeo) 327.51s 960.01s 640.85s
Muda wa majibu (jumla) 1442.48s 2561.63s 3825.81s
Vigezo 975B jumla (41B vinavyotumika) 27.8B 27.3B
Upatikanaji Chanzo huria Chanzo huria Uzani unapatikana

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.

#136 Thinking Machines: Inkling

high
Gharama
$0.005
Muda
32.2s
Tokeni
1,275 tok

#160 DaisyRose 27B

xhigh
Gharama
$0.063
Muda
189.8s
Tokeni
33,346 tok

#104 Qwen3.8 27B

high
Gharama
~$0.008
Muda
270.1s
Tokeni
18,963 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
Inkling 8.5 10.0 66.7% 0 148.36s 7,374 430 78,982
DaisyRose 27B 9.9 10.0 100.0% 0 99.76s 8,235 497 147,458
Qwen3.8 27B 8.1 7.0 88.9% 1 248.62s 8,235 346 143,335

Badilisha jozi ya ulinganisho

GPT-5.2mediumvsQwen3.8 27BhighInapatikana bureSeed-2.0-CodelowvsDaisyRose 27BxhighQwen3.8 27BhighInapatikana burevsMiMo-V2.6-PromediumSeed 2.1 TurbomediumvsQwen3.8 27BhighInapatikana bureGPT-6 SollowvsQwen3.8 27BhighInapatikana bureGemini 3.1 Pro PreviewmediumvsInklinghighInapatikana bureParticle-1xhighvsQwen3.8 27BhighInapatikana bureKimi K3.1 ProhighvsDaisyRose 27BxhighSeed-2.0-LitemediumvsDaisyRose 27BxhighMuse Glimmer 30BxhighvsInklinghighInapatikana bureGPT-5 MinimediumvsInklinghighInapatikana bureMuse EmberlowvsQwen3.8 27BhighInapatikana bure