Urambazaji
AI BENCHY
Advertise here

DeepSeek V4 Flash 0731 (low) vs GPT-5.2 (medium)

GPT-5.2 (medium) inaongoza kwa average score: 8.4 vs 8.2. DeepSeek V4 Flash 0731 (low) ina gharama ya chini ya benchmark: $0.053 vs $0.951. GPT-5.2 (medium) ni ya haraka zaidi: 22.62s vs 60.18s, na pass rates 75.8% vs 72.7%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-01

Nafasi
#32
Jumla ya tokeni za matokeo
314,605
Muda wa majibu (wastani)
60.18s
Jumla ya gharama
$0.053
Nafasi
#27
Jumla ya tokeni za matokeo
54,782
Muda wa majibu (wastani)
22.62s
Jumla ya gharama
$0.951
Muundo unaopendekezwa DeepSeek V4 Flash 0731 (low)

Its score stays close to the best score here (8.2 vs 8.4), while costing about 18.2x less than GPT-5.2 (medium).

Ulinganisho wa kina

Kipimo DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 low Toleo: 2026-08-01 GPT-5.2 GPT-5.2 medium Toleo: 2025-12-11
Alama 8.2 8.4
Nafasi #32 #27
Uaminifu 10.0 10.0
Uthabiti 8.3 8.5
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 75.8% 72.7%
Majaribio yasiyo thabiti 5 4
Jumla ya uendeshaji 66 66
Gharama kwa matokeo 0.374 6.791
Jumla ya gharama $0.053 $0.951
Bei ya ingizo $0.140 / 1M $1.750 / 1M
Bei ya toleo $0.280 / 1M $14.000 / 1M
Jumla ya tokeni za ingizo 93,336 105,004
Tokeni za matokeo 40,662 9,914
Tokeni za hoja 273,943 44,868
Muda wa majibu (wastani) 60.18s 22.62s
Muda wa majibu (upeo) 438.65s 102.93s
Muda wa majibu (jumla) 1323.92s 339.28s

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#32 DeepSeek V4 Flash 0731

low
SVG batili
Gharama
$0.000
Muda
78.1s
Tokeni
8,090 tok

#27 GPT-5.2

medium
Gharama
$0.047
Muda
49.2s
Tokeni
3,396 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
DeepSeek V4 Flash 0731 7.3 5.1 77.8% 2 163.31s 5,953 782 86,028
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho