Urambazaji
Advertise here

Kimi K3.1 Pro (max) vs Qwen3.8 27B (high)

Kimi K3.1 Pro (max) inaongoza kwa average score: 8.7 vs 8.7. Qwen3.8 27B (high) ina gharama ya chini ya benchmark: ~$0.298 vs $3.578. Kimi K3.1 Pro (max) ni ya haraka zaidi: 152.72s vs 166.34s, na pass rates 84.1% vs 78.3%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-24

Modeli zilizolinganishwa

Nafasi
#66
Jumla ya tokeni za matokeo
300,622
Muda wa majibu (wastani)
152.72s
Jumla ya gharama
$3.578
Nafasi
#69
Jumla ya tokeni za matokeo
677,080
Muda wa majibu (wastani)
166.34s
Jumla ya gharama
~$0.298
Muundo unaopendekezwa Qwen3.8 27B (high)

Its score stays close to the best score here (8.7 vs 8.7), while costing about 12.0x less than Kimi K3.1 Pro (max).

Ulinganisho wa kina

Kipimo Kimi K3.1 Pro Kimi K3.1 Pro max Toleo: 2026-10-24 Qwen3.8 27B Qwen3.8 27B high Toleo: 2026-08-14 Inapatikana bure
Alama 8.7 8.7
Nafasi #66 #69
Uaminifu 7.1 9.7
Uthabiti 8.6 9.2
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 84.1% 78.3%
Majaribio yasiyo thabiti 4 2
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 21.043 ~1.751
Jumla ya gharama $3.578 ~$0.298
Bei ya ingizo $2.000 / 1M Haipo
Bei ya toleo $10.000 / 1M Haipo
Bei ya kusoma akiba $0.200 / 1M Haipo
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 285,488 348,967
Tokeni za matokeo 9,091 1,005
Tokeni za hoja 291,531 676,075
Muda wa majibu (wastani) 152.72s 166.34s
Muda wa majibu (upeo) 960.13s 640.85s
Muda wa majibu (jumla) 3512.51s 3825.81s
Vigezo ~2.8T jumla (~104B vinavyotumika) 27.3B
Upatikanaji Imefungwa 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.

#66 MoonshotAI: Kimi K3.1 Pro

max
Gharama
$0.193
Muda
387.5s
Tokeni
19,362 tok

#69 Qwen3.8 27B

high
Gharama
~$0.008
Muda
270.1s
Tokeni
18,963 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
Kimi K3.1 Pro 10.0 10.0 100.0% 0 71.94s 8,061 467 31,621
Qwen3.8 27B 8.1 7.0 88.9% 1 248.62s 8,235 346 143,335

Badilisha jozi ya ulinganisho

GPT-5.2mediumvsQwen3.8 27BhighInapatikana bureQwen3.8 27BhighInapatikana burevsMiMo-V2.6-PromediumMuse Spark 1.2lowvsKimi K3.1 PromaxSeed 2.1 TurbomediumvsQwen3.8 27BhighInapatikana bureDeepSeek V4.1 FlashmediumvsKimi K3.1 PromaxDeepSeek V4.1 FlashhighvsKimi K3.1 PromaxGPT-6 SollowvsQwen3.8 27BhighInapatikana bureMuse Spark OpenmediumvsKimi K3.1 PromaxDeepSeek V4.1 FlashmaxvsQwen3.8 27BhighInapatikana bureMuse Spark 1.2lowvsQwen3.8 27BhighInapatikana bureKimi K3.1 PromaxvsGPT-5.4mediumKimi K3.1 PromaxvsGPT-5.2medium