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

D1 (default) vs Decider V1.1 27B (default)

Decider V1.1 27B (default) inaongoza kwa average score: 2.6 vs 1.9. Decider V1.1 27B (default) ina gharama ya chini ya benchmark: $0.002 vs $0.003. Decider V1.1 27B (default) ni ya haraka zaidi: 320ms vs 508ms, na pass rates 11.6% vs 17.4%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-07

Modeli zilizolinganishwa

Nafasi
#399
Jumla ya tokeni za matokeo
0
Muda wa majibu (wastani)
508ms
Jumla ya gharama
$0.003
Nafasi
#395
Jumla ya tokeni za matokeo
69
Muda wa majibu (wastani)
320ms
Jumla ya gharama
$0.002
Muundo unaopendekezwa Decider V1.1 27B (default)

It has the best score here (2.6), while costing about 1.5x less than D1 (default).

Ulinganisho wa kina

Kipimo D1 D1 default Toleo: 2026-10-02 Decider V1.1 27B Decider V1.1 27B default Toleo: 2026-10-07
Alama 1.9 2.6
Nafasi #399 #395
Uaminifu 10.0 10.0
Uthabiti 4.9 5.2
Majaribio 36/69 36/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 11.6% 17.4%
Majaribio yasiyo thabiti 1 0
Jumla ya uendeshaji 36 36
Gharama kwa matokeo 0.112 0.037
Jumla ya gharama $0.003 $0.002
Bei ya ingizo $0.040 / 1M $0.020 / 1M
Bei ya toleo $0.000 / 1M $0.000 / 1M
Bei ya kusoma akiba $0.040 / 1M Haipo
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 55,956 73,557
Tokeni za matokeo 0 69
Tokeni za hoja 0 0
Muda wa majibu (wastani) 508ms 320ms
Muda wa majibu (upeo) 820ms 491ms
Muda wa majibu (jumla) 6.10s 3.84s
Vigezo - 27B
Upatikanaji Imefungwa 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.

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
D1 2.2 6.7 0.0% 0 456ms 25,605 0 0
Decider V1.1 27B 4.9 6.7 33.3% 0 305ms 32,733 12 0

Badilisha jozi ya ulinganisho

Gemini 3 Flash PreviewhighvsD1defaultCommand A+lowvsDecider V1.1 27BdefaultCommand A+nonevsDecider V1.1 27BdefaultCommand A+highvsDecider V1.1 27BdefaultGemini 3 Flash PreviewhighvsDecider V1.1 27BdefaultCommand A+mediumvsDecider V1.1 27BdefaultDecider V1.1 27BdefaultvsGrok 4.20noneLing 3.0 TinymediumvsDecider V1.1 27BdefaultCommand A+lowvsD1defaultLing 3.0 TinylowvsDecider V1.1 27BdefaultCommand A+nonevsD1defaultLing 3.0 TinyhighvsDecider V1.1 27Bdefault