Urambazaji
Advertise here

DeepSeek V4.1 Flash 1017 (high) vs Qwen3.8 2.4T A95B (high)

average score iko karibu sawa: 7.8 vs 7.9. DeepSeek V4.1 Flash 1017 (high) ina gharama ya chini ya benchmark: $0.589 vs $2.949. DeepSeek V4.1 Flash 1017 (high) ni ya haraka zaidi: 58.56s vs 120.88s, na pass rates 71.0% vs 75.4%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-19

Modeli zilizolinganishwa

Nafasi
#126
Jumla ya tokeni za matokeo
911,334
Muda wa majibu (wastani)
58.56s
Jumla ya gharama
$0.589
Nafasi
#122
Jumla ya tokeni za matokeo
368,836
Muda wa majibu (wastani)
120.88s
Jumla ya gharama
$2.949
Muundo unaopendekezwa DeepSeek V4.1 Flash 1017 (high)

It has the best score here (7.8), while costing about 5.0x less than Qwen3.8 2.4T A95B (high).

Ulinganisho wa kina

Kipimo DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 high Toleo: 2026-10-18 Qwen3.8 2.4T A95B Qwen3.8 2.4T A95B high Toleo: 2026-08-12
Alama 7.8 7.9
Nafasi #126 #122
Uaminifu 10.0 9.6
Uthabiti 7.8 8.4
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 71.0% 75.4%
Majaribio yasiyo thabiti 6 4
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 4.530 18.696
Jumla ya gharama $0.589 $2.949
Bei ya ingizo $0.150 / 1M $2.000 / 1M
Bei ya toleo $0.600 / 1M $6.000 / 1M
Bei ya kusoma akiba $0.003 / 1M $0.250 / 1M
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 279,873 295,642
Tokeni za matokeo 7,049 115,041
Tokeni za hoja 904,285 353,398
Muda wa majibu (wastani) 58.56s 120.88s
Muda wa majibu (upeo) 440.77s 532.28s
Muda wa majibu (jumla) 1346.87s 2780.16s
Vigezo ~748B jumla (~16B vinavyotumika) 2.4T jumla (95B vinavyotumika)
Upatikanaji Chanzo huria Uzani unapatikana

Bei za akiba zinahusu tokeni za ingizo. Kusoma hutumia tena maelekezo yaliyohifadhiwa; kuandika huyahifadhi na kunaweza kuongeza gharama. Tokeni za matokeo hutumia bei ya matokeo.

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#126 DeepSeek V4.1 Flash 1017

high
Gharama
$0.004
Muda
27.2s
Tokeni
7,593 tok

#122 Qwen3.8 2.4T A95B

high
Reached the allocated time limit (600 seconds) without receiving showcase output.
Gharama
$0.000
Muda
600.0s
Tokeni
0 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 V4.1 Flash 1017 4.5 1.4 66.7% 3 196.67s 7,434 217 446,179
Qwen3.8 2.4T A95B 5.9 6.3 55.6% 1 160.52s 6,399 3,310 48,078

Badilisha jozi ya ulinganisho