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

KAT-Coder-Air V2.5 (medium) vs Qwen3.8 27B

average score iko karibu sawa: 5.6 vs 5.5. Gharama ya maunzi ya ndani haikupimwa, kwa hiyo ulinganisho wa gharama haupatikani. Qwen3.8 27B ni ya haraka zaidi: 3.12s vs 8.65s, na pass rates 45.5% vs 40.9%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-15

Nafasi
#207
Jumla ya tokeni za matokeo
66,576
Muda wa majibu (wastani)
8.65s
Jumla ya gharama
$0.048
Nafasi
#211
Jumla ya tokeni za matokeo
11,445
Muda wa majibu (wastani)
3.12s
Jumla ya gharama
Haipo
Muundo unaopendekezwa Qwen3.8 27B

It has the best score here (5.5), while responding about 2.8x faster than KAT-Coder-Air V2.5 (medium).

Ulinganisho wa kina

Kipimo KAT-Coder-Air V2.5 KAT-Coder-Air V2.5 medium Toleo: 2026-07-14 Qwen3.8 27B Qwen3.8 27B none Toleo: 2026-08-14
Alama 5.6 5.5
Nafasi #207 #211
Uaminifu 9.6 10.0
Uthabiti 8.9 10.0
Majaribio 66/66 66/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 45.5% 40.9%
Majaribio yasiyo thabiti 3 0
Jumla ya uendeshaji 66 66
Gharama kwa matokeo 0.596 Haipo
Jumla ya gharama $0.048 Haipo
Bei ya ingizo $0.150 / 1M Haipo
Bei ya toleo $0.600 / 1M Haipo
Jumla ya tokeni za ingizo 51,369 122,463
Tokeni za matokeo 8,008 11,445
Tokeni za hoja 58,568 0
Muda wa majibu (wastani) 8.65s 3.12s
Muda wa majibu (upeo) 48.19s 44.76s
Muda wa majibu (jumla) 190.35s 68.69s
Vigezo ~35B jumla (~3B vinavyotumika) 27.3B
Upatikanaji Imefungwa Uzani unapatikana

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#207 KAT-Coder-Air V2.5

medium
Gharama
$0.003
Muda
23.7s
Tokeni
4,924 tok

#211 Qwen3.8 27B

none
Gharama
Haipo
Muda
23.9s
Tokeni
1,922 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
KAT-Coder-Air V2.5 3.6 7.0 22.2% 1 23.37s 7,893 5,199 29,973
Qwen3.8 27B 5.5 10.0 33.3% 0 1.19s 7,911 408 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho