Urambazaji
AI BENCHY
Advertise here

OpenAI: GPT-5.4 vs StepFun: Step 3.5 Flash

Step 3.5 Flash (medium) inaongoza kwa average score: 6.0 vs 5.8. Step 3.5 Flash (medium) ina gharama ya chini ya benchmark: $0.108 vs $0.397. GPT-5.4 ni ya haraka zaidi: 2.07s vs 174.22s, na pass rates 34.9% vs 51.5%.

Muundo unaopendekezwaGPT-5.4Its score stays close to the best score here (5.8 vs 6.0), while responding about 84.2x faster than Step 3.5 Flash (medium).

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-07-18

Kipimo GPT-5.4 GPT-5.4 none Toleo: 2026-03-05 Step 3.5 Flash Step 3.5 Flash medium Toleo: 2026-02-01
Alama 5.8 6.0
Nafasi #135 #126
Uaminifu 10.0 9.2
Uthabiti 9.2 9.0
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 34.9% 51.5%
Majaribio yasiyo thabiti 2 1
Jumla ya uendeshaji 66 63
Gharama kwa matokeo 5.663 0.540
Jumla ya gharama $0.397 $0.108
Bei ya ingizo $2.500 / 1M $0.100 / 1M
Bei ya toleo $15.000 / 1M $0.300 / 1M
Jumla ya tokeni za ingizo 108,632 65,707
Tokeni za matokeo 8,321 108,561
Tokeni za hoja 0 293,993
Muda wa majibu (wastani) 2.07s 174.22s
Muda wa majibu (upeo) 15.63s 1597.85s
Muda wa majibu (jumla) 45.51s 2613.32s

Hamster playing table tennis

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

#135 GPT-5.4

none
Gharama
$0.026
Muda
18.1s
Tokeni
1,792 tok

#126 Step 3.5 Flash

medium
Gharama
$0.008
Muda
277.1s
Tokeni
23,695 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-5.4 5.5 10.0 33.3% 0 1.62s 7,305 516 0
Step 3.5 Flash 2.4 5.2 0.0% 0 258.38s 2,211 13,207 22,429

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho