Urambazaji
Advertise here

Qwen3.6 27B (medium) vs Step 3.7 Flash (low)

average score iko karibu sawa: 7.2 vs 7.2. Step 3.7 Flash (low) ina gharama ya chini ya benchmark: $0.449 vs $1.006. Step 3.7 Flash (low) ni ya haraka zaidi: 20.72s vs 107.79s, na pass rates 62.3% vs 63.8%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-01

Modeli zilizolinganishwa

Nafasi
#148
Jumla ya tokeni za matokeo
287,899
Muda wa majibu (wastani)
107.79s
Jumla ya gharama
$1.006
Nafasi
#147
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 2.2x less than Qwen3.6 27B (medium).

Ulinganisho wa kina

Kipimo Qwen3.6 27B Qwen3.6 27B medium Toleo: 2026-04-20 Step 3.7 Flash Step 3.7 Flash low Toleo: 2026-05-29
Alama 7.2 7.2
Nafasi #148 #147
Uaminifu 10.0 10.0
Uthabiti 7.7 7.9
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 62.3% 63.8%
Majaribio yasiyo thabiti 7 6
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 7.677 4.078
Jumla ya gharama $1.006 $0.449
Bei ya ingizo $0.320 / 1M $0.200 / 1M
Bei ya toleo $3.200 / 1M $1.150 / 1M
Jumla ya tokeni za ingizo 264,147 292,685
Tokeni za matokeo 34,419 339,108
Tokeni za hoja 253,480 0
Muda wa majibu (wastani) 107.79s 20.72s
Muda wa majibu (upeo) 1085.11s 124.75s
Muda wa majibu (jumla) 2479.26s 476.67s
Vigezo 27B 198B jumla (11B vinavyotumika)
Upatikanaji Chanzo huria Chanzo huria

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#148 Qwen3.6 27B

medium
Gharama
$0.009
Muda
39.6s
Tokeni
3,090 tok

#147 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
Qwen3.6 27B 7.7 10.0 66.7% 0 142.99s 5,051 7,968 43,367
Step 3.7 Flash 8.2 7.2 88.9% 1 9.46s 7,437 18,685 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho