Urambazaji
AI BENCHY
Advertise here

Modeli zilizolinganishwa

Ulinganisho wa benchmark DeepSeek V4 Flash (high) vs DeepSeek V4 Pro (high) vs Kimi K2.6 (medium) vs GLM 5 (medium): GLM 5 (medium) inaongoza kwenye Alama kwa 7.7. DeepSeek V4 Flash (high) inaongoza kwenye Uaminifu kwa 10.0. DeepSeek V4 Flash (high) ina Jumla ya gharama ya chini zaidi kwa $0.060. GLM 5 (medium) ndiyo ya haraka zaidi kwa 33.54s.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-07

Nafasi
#62
Jumla ya tokeni za matokeo
168,165
Muda wa majibu (wastani)
49.75s
Jumla ya gharama
$0.060
Nafasi
#63
Jumla ya tokeni za matokeo
189,181
Muda wa majibu (wastani)
79.14s
Jumla ya gharama
$0.200
Nafasi
#88
Jumla ya tokeni za matokeo
391,540
Muda wa majibu (wastani)
109.98s
Jumla ya gharama
$0.746
Nafasi
#59
Jumla ya tokeni za matokeo
124,566
Muda wa majibu (wastani)
33.54s
Jumla ya gharama
$0.307
Muundo unaopendekezwa DeepSeek V4 Flash (high)

Its score stays close to the best score here (7.7 vs 7.7), while costing about 7.0x less than miundo mingine katika ulinganisho huu.

Ulinganisho wa kina

Kipimo DeepSeek V4 Flash DeepSeek V4 Flash high Toleo: 2026-04-24 DeepSeek V4 Pro DeepSeek V4 Pro high Toleo: 2026-04-24 Kimi K2.6 Kimi K2.6 medium Toleo: 2026-04-20 GLM 5 GLM 5 medium Toleo: 2026-02-12
Alama 7.7 7.7 7.2 7.7
Nafasi #62 #63 #88 #59
Uaminifu 10.0 10.0 9.4 10.0
Uthabiti 8.2 7.7 8.3 8.1
Ufunikaji wa benchmark majaribio 22/22 · marudio 66/66 majaribio 22/22 · marudio 66/66 majaribio 22/22 · marudio 66/66 majaribio 21/22 · marudio 63/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 72.7% 63.6% 63.6% 78.8%
Majaribio yasiyo thabiti 5 6 4 4
Jumla ya uendeshaji 66 66 66 63
Gharama kwa matokeo 0.402 2.000 9.821 1.668
Jumla ya gharama $0.060 $0.200 $0.746 $0.307
Bei ya ingizo $0.140 / 1M $0.435 / 1M $0.580 / 1M $0.950 / 1M
Bei ya toleo $0.280 / 1M $0.870 / 1M $2.440 / 1M $2.551 / 1M
Jumla ya tokeni za ingizo 108,392 90,748 68,902 35,224
Tokeni za matokeo 14,478 10,462 111,680 21,570
Tokeni za hoja 153,687 178,719 279,860 102,996
Muda wa majibu (wastani) 49.75s 79.14s 109.98s 33.54s
Muda wa majibu (upeo) 218.13s 416.76s 876.20s 99.85s
Muda wa majibu (jumla) 1094.41s 1740.97s 2309.56s 435.99s

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#62 DeepSeek V4 Flash

high
Gharama
$0.003
Muda
93.1s
Tokeni
7,926 tok

#63 DeepSeek V4 Pro

high
Gharama
$0.023
Muda
257.6s
Tokeni
14,870 tok

#88 MoonshotAI: Kimi K2.6

medium
Gharama
$0.013
Muda
103.4s
Tokeni
3,620 tok

#59 GLM 5

medium
Gharama
$0.005
Muda
20.7s
Tokeni
2,068 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 7.8 10.0 66.7% 0 50.60s 7,279 395 34,862
DeepSeek V4 Pro 6.3 8.7 33.3% 0 243.00s 5,090 383 84,580
Kimi K2.6 5.7 8.6 33.3% 0 214.42s 2,925 9,970 77,189
GLM 5 10.0 10.0 100.0% 0 74.30s 7,254 2,997 52,930

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho