Urambazaji
Advertise here

DeepSeek V4 Flash 0731 (medium) vs GPT-6 Luna (high)

DeepSeek V4 Flash 0731 (medium) inaongoza kwa average score: 7.8 vs 7.7. GPT-6 Luna (high) ina gharama ya chini ya benchmark: $0.074 vs $0.462. GPT-6 Luna (high) ni ya haraka zaidi: 20.37s vs 94.16s, na pass rates 72.5% vs 73.9%.

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

Modeli zilizolinganishwa

Nafasi
#110
Jumla ya tokeni za matokeo
577,214
Muda wa majibu (wastani)
94.16s
Jumla ya gharama
$0.462
Nafasi
#111
Jumla ya tokeni za matokeo
101,587
Muda wa majibu (wastani)
20.37s
Jumla ya gharama
$0.074
Muundo unaopendekezwa GPT-6 Luna (high)

Its score stays close to the best score here (7.7 vs 7.8), while costing about 6.3x less than DeepSeek V4 Flash 0731 (medium).

Ulinganisho wa kina

Kipimo DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 medium Toleo: 2026-08-01 GPT-6 Luna GPT-6 Luna high Toleo: 2026-09-23
Alama 7.8 7.7
Nafasi #110 #111
Uaminifu 10.0 10.0
Uthabiti 7.2 8.7
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 72.5% 73.9%
Majaribio yasiyo thabiti 8 4
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 1.176 0.492
Jumla ya gharama $0.462 $0.074
Bei ya ingizo $0.010 / 1M $0.100 / 1M
Bei ya toleo $1.280 / 1M $0.500 / 1M
Jumla ya tokeni za ingizo 274,189 229,986
Tokeni za matokeo 66,689 6,037
Tokeni za hoja 510,525 95,550
Muda wa majibu (wastani) 94.16s 20.37s
Muda wa majibu (upeo) 303.26s 106.93s
Muda wa majibu (jumla) 2165.72s 468.52s
Vigezo 284B jumla (13B vinavyotumika) ~400B jumla (~17B vinavyotumika)
Upatikanaji Imefungwa Imefungwa

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#110 DeepSeek V4 Flash 0731

medium
Gharama
$0.004
Muda
93.3s
Tokeni
13,252 tok

#111 GPT-6 Luna

high
Gharama
$0.003
Muda
49.2s
Tokeni
5,231 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 6.4 4.4 77.8% 2 198.78s 6,032 4,109 160,154
GPT-6 Luna 7.8 7.4 77.8% 1 24.69s 7,302 483 15,691

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho