Urambazaji
AI BENCHY
Advertise here

Step 3.7 Flash (high) vs GLM 5.3 (low)

Step 3.7 Flash (high) inaongoza kwa average score: 6.8 vs 6.8. GLM 5.3 (low) ina gharama ya chini ya benchmark: $0.257 vs $1.229. GLM 5.3 (low) ni ya haraka zaidi: 13.65s vs 70.10s, na pass rates 60.6% vs 65.2%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-20

Nafasi
#129
Jumla ya tokeni za matokeo
1,050,900
Muda wa majibu (wastani)
70.10s
Jumla ya gharama
$1.229
Nafasi
#134
Jumla ya tokeni za matokeo
24,808
Muda wa majibu (wastani)
13.65s
Jumla ya gharama
$0.257
Muundo unaopendekezwa GLM 5.3 (low)

Its score stays close to the best score here (6.8 vs 6.8), while costing about 4.8x less than Step 3.7 Flash (high).

Ulinganisho wa kina

Kipimo Step 3.7 Flash Step 3.7 Flash high Toleo: 2026-05-29 GLM 5.3 GLM 5.3 low Toleo: 2026-08-20
Alama 6.8 6.8
Nafasi #129 #134
Uaminifu 10.0 10.0
Uthabiti 8.4 8.5
Majaribio 66/66 66/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 60.6% 65.2%
Majaribio yasiyo thabiti 4 4
Jumla ya uendeshaji 66 66
Gharama kwa matokeo 11.167 2.135
Jumla ya gharama $1.229 $0.257
Bei ya ingizo $0.200 / 1M $1.400 / 1M
Bei ya toleo $1.150 / 1M $4.400 / 1M
Jumla ya tokeni za ingizo 98,700 104,989
Tokeni za matokeo 1,050,900 8,532
Tokeni za hoja 0 16,276
Muda wa majibu (wastani) 70.10s 13.65s
Muda wa majibu (upeo) 364.99s 83.60s
Muda wa majibu (jumla) 1542.14s 300.22s
Vigezo 198B jumla (11B vinavyotumika) 744B jumla (40B vinavyotumika)
Upatikanaji Chanzo huria Imefungwa

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#129 Step 3.7 Flash

high
Gharama
$0.007
Muda
63.6s
Tokeni
6,030 tok

#134 GLM 5.3

low
Gharama
$0.007
Muda
28.4s
Tokeni
1,599 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
Step 3.7 Flash 4.0 6.0 22.2% 1 206.21s 6,057 327,340 0
GLM 5.3 6.2 6.9 55.6% 1 21.02s 7,317 368 6,764

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho