Urambazaji
Advertise here

Qwen3.5-122B-A10B (medium) vs Step 3.7 Flash (low)

Step 3.7 Flash (low) inaongoza kwa average score: 7.2 vs 7.0. Step 3.7 Flash (low) ina gharama ya chini ya benchmark: $0.449 vs $1.152. Step 3.7 Flash (low) ni ya haraka zaidi: 20.72s vs 66.96s, na pass rates 71.0% vs 63.8%.

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

Modeli zilizolinganishwa

Nafasi
#193
Jumla ya tokeni za matokeo
522,190
Muda wa majibu (wastani)
66.96s
Jumla ya gharama
$1.152
Nafasi
#179
Jumla ya tokeni za matokeo
339,108
Muda wa majibu (wastani)
20.72s
Jumla ya gharama
$0.449
Muundo unaopendekezwa Step 3.7 Flash (low)

It has the best score here (7.2), while costing about 2.6x less than Qwen3.5-122B-A10B (medium).

Ulinganisho wa kina

Kipimo Qwen3.5-122B-A10B Qwen3.5-122B-A10B medium Toleo: 2026-02-24 Step 3.7 Flash Step 3.7 Flash low Toleo: 2026-05-29
Alama 7.0 7.2
Nafasi #193 #179
Uaminifu 10.0 10.0
Uthabiti 8.3 7.9
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 71.0% 63.8%
Majaribio yasiyo thabiti 5 6
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 9.196 4.078
Jumla ya gharama $1.152 $0.449
Bei ya ingizo $0.260 / 1M $0.200 / 1M
Bei ya toleo $2.080 / 1M $1.150 / 1M
Bei ya kusoma akiba Haipo $0.040 / 1M
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 251,695 292,685
Tokeni za matokeo 49,415 339,108
Tokeni za hoja 472,775 0
Muda wa majibu (wastani) 66.96s 20.72s
Muda wa majibu (upeo) 519.30s 124.75s
Muda wa majibu (jumla) 1539.99s 476.67s
Vigezo 122B jumla (10B vinavyotumika) 198B jumla (11B vinavyotumika)
Upatikanaji Chanzo huria 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.

#193 Qwen3.5-122B-A10B

medium
Gharama
$0.019
Muda
48.7s
Tokeni
6,034 tok

#179 Step 3.7 Flash

low
SVG batili
Gharama
$0.004
Muda
25.3s
Tokeni
3,072 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
Qwen3.5-122B-A10B 6.0 7.2 55.6% 1 114.48s 7,630 8,057 82,578
Step 3.7 Flash 8.2 7.2 88.9% 1 9.46s 7,437 18,685 0

Badilisha jozi ya ulinganisho