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

GPT-6 Luna (medium) vs Qwen3.6 35B A3B (medium)

GPT-6 Luna (medium) inaongoza kwa average score: 8.3 vs 6.5. GPT-6 Luna (medium) ina gharama ya chini ya benchmark: $0.047 vs $0.834. GPT-6 Luna (medium) ni ya haraka zaidi: 18.07s vs 59.92s, na pass rates 73.9% vs 58.0%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-24

Modeli zilizolinganishwa

Nafasi
#97
Jumla ya tokeni za matokeo
53,161
Muda wa majibu (wastani)
18.07s
Jumla ya gharama
$0.047
Nafasi
#232
Jumla ya tokeni za matokeo
769,570
Muda wa majibu (wastani)
59.92s
Jumla ya gharama
$0.834
Muundo unaopendekezwa GPT-6 Luna (medium)

It has the best score here (8.3), while costing about 17.8x less than Qwen3.6 35B A3B (medium).

Ulinganisho wa kina

Kipimo GPT-6 Luna GPT-6 Luna medium Toleo: 2026-09-23 Qwen3.6 35B A3B Qwen3.6 35B A3B medium Toleo: 2026-04-20
Alama 8.3 6.5
Nafasi #97 #232
Uaminifu 10.0 10.0
Uthabiti 8.9 9.0
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 73.9% 58.0%
Majaribio yasiyo thabiti 3 3
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 0.313 6.732
Jumla ya gharama $0.047 $0.834
Bei ya ingizo $0.100 / 1M $0.150 / 1M
Bei ya toleo $0.500 / 1M $1.000 / 1M
Bei ya kusoma akiba $0.010 / 1M $0.050 / 1M
Bei ya kuandika akiba $0.125 / 1M Haipo
Jumla ya tokeni za ingizo 203,193 282,192
Tokeni za matokeo 5,751 75,306
Tokeni za hoja 47,410 700,868
Muda wa majibu (wastani) 18.07s 59.92s
Muda wa majibu (upeo) 66.44s 817.57s
Muda wa majibu (jumla) 415.53s 1258.32s
Vigezo ~400B jumla (~17B vinavyotumika) 35B jumla (3B vinavyotumika)
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.

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#97 GPT-6 Luna

medium
Gharama
$0.002
Muda
23.6s
Tokeni
2,966 tok

#232 Qwen3.6 35B A3B

medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
Gharama
$0.000
Muda
300.0s
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

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 Luna 6.6 4.6 77.8% 2 23.63s 7,302 438 10,222
Qwen3.6 35B A3B 7.7 10.0 66.7% 0 50.55s 5,051 7,929 37,223

Badilisha jozi ya ulinganisho